Abstract:   We present a new approach to the analysis of dynamic facial images for the purposes of estimating and resynthesizing dynamic facial expressions. The approach exploits a sophisticated generative model of the human face originally developed for realistic facial animation. The face model, which may be simulated and rendered at interactive rates on a graphics workstation, incorporates a physics-based synthetic facial tissue and a set of anatomically motivated facial muscle actuators. We consider the estimation of dynamic facial muscle contractions from video sequences of expressive human faces. We develop an estimation technique that uses deformable contour models (snakes) to track the nonrigid motions of facial features in video images. The technique estimates muscle actuator controls with sufficient accuracy to permit the face model to resynthesize transient expressions.

Abstract:   We present a new approach to the analysis of dynamic facial images for the purposes of estimating and resynthesizing dynamic facial expressions. The approach exploits a sophisticated generative model of the human face originally developed for realistic facial animation. The face model, which may be simulated and rendered at interactive rates on a graphics workstation, incorporates a physics-based synthetic facial tissue and a set of anatomically motivated facial muscle actuators. We consider the estimation of dynamic facial muscle contractions from video sequences of expressive human faces. We develop an estimation technique that uses deformable contour models (snakes) to track the nonrigid motions of facial features in video images. The technique estimates muscle actuator controls with sufficient accuracy to permit the face model to resynthesize transient expressions.

Abstract:   We present a new approach to the analysis of dynamic facial images for the purposes of estimating and resynthesizing dynamic facial expressions. The approach exploits a sophisticated generative model of the human face originally developed for realistic facial animation. The face model, which may be simulated and rendered at interactive rates on a graphics workstation, incorporates a physics-based synthetic facial tissue and a set of anatomically motivated facial muscle actuators. We consider the estimation of dynamic facial muscle contractions from video sequences of expressive human faces. We develop an estimation technique that uses deformable contour models (snakes) to track the nonrigid motions of facial features in video images. The technique estimates muscle actuator controls with sufficient accuracy to permit the face model to resynthesize transient expressions.

Abstract:   We present a new approach to the analysis of dynamic facial images for the purposes of estimating and resynthesizing dynamic facial expressions. The approach exploits a sophisticated generative model of the human face originally developed for realistic facial animation. The face model, which may be simulated and rendered at interactive rates on a graphics workstation, incorporates a physics-based synthetic facial tissue and a set of anatomically motivated facial muscle actuators. We consider the estimation of dynamic facial muscle contractions from video sequences of expressive human faces. We develop an estimation technique that uses deformable contour models (snakes) to track the nonrigid motions of facial features in video images. The technique estimates muscle actuator controls with sufficient accuracy to permit the face model to resynthesize transient expressions.

Abstract:   We present a new approach to the analysis of dynamic facial images for the purposes of estimating and resynthesizing dynamic facial expressions. The approach exploits a sophisticated generative model of the human face originally developed for realistic facial animation. The face model, which may be simulated and rendered at interactive rates on a graphics workstation, incorporates a physics-based synthetic facial tissue and a set of anatomically motivated facial muscle actuators. We consider the estimation of dynamic facial muscle contractions from video sequences of expressive human faces. We develop an estimation technique that uses deformable contour models (snakes) to track the nonrigid motions of facial features in video images. The technique estimates muscle actuator controls with sufficient accuracy to permit the face model to resynthesize transient expressions.

Abstract:   We present a new approach to the analysis of dynamic facial images for the purposes of estimating and resynthesizing dynamic facial expressions. The approach exploits a sophisticated generative model of the human face originally developed for realistic facial animation. The face model, which may be simulated and rendered at interactive rates on a graphics workstation, incorporates a physics-based synthetic facial tissue and a set of anatomically motivated facial muscle actuators. We consider the estimation of dynamic facial muscle contractions from video sequences of expressive human faces. We develop an estimation technique that uses deformable contour models (snakes) to track the nonrigid motions of facial features in video images. The technique estimates muscle actuator controls with sufficient accuracy to permit the face model to resynthesize transient expressions.

Abstract:   Model-based image coding applied to interpersonal communication achieves very low bit-rate image transmission. To accomplish it, accurate three-dimensional (3-D) motion estimation of a speaker is necessary. A new method of 3-D motion estimation is presented, consisting of two steps. In the first, facial contours and feature points of a speaker are extracted using filtering and Snake algorithms. Five feature points on a speaker's facial image are tracked between consecutive picture frames, which gives 2-D motion vectors of the feature points. Then, in the second step, the 3-D motion of a speaker's head is estimated using a three-layered neural network model, after training with many possible motion patterns of the human head using an existing 3-D general shape model. Experimental results show that our method not only achieves good results but is also more robust than existing methods, even when the motion of an object is rather large or complicated. Accurately estimated 3-D motion parameters can realise image transmission at a very low bit rate.

Abstract:   Many problems in computational vision (including stereo correspondence, motion analysis and surface reconstruction) can be solved effectively using a constrained optimization approach, where smoothness is the common constraint. Moreover, these problems can be cast in a variational form that minimizes an energy functional. Unfortunately, standard optimization techniques tend to find only local energy minima. Coarse to fine scale space tracking (where energy minima at reduced resolution are found and successively tracked to higher resolution) has been demonstrated to find solutions of practical value. For smoothness-constrained optimization problems, we show that scale space tracking can be implicitly implemented by appropriately adjusting the smoothness constraint. A useful physical model for controlled smoothness (deformable sheets) provides a natural framework for scale space tracking and addressing many vision problems that can be solved by appealing to a smoothness constraint. Deformable sheets are characterized by a global energy functional, and the smoothness constraint is represented by a linear internal energy term. In analogy to physical sheets, the model sheets are deformed by problem specific external forces and, in turn, impose smoothness on the applied forces. We have related deformable sheet smoothness properties to Gaussian blurring (the common expression of scale) and used this relationship to unify the concepts of scale and smoothness. In our formulation, the smoothness/scale state is controlled by a single parameter in the deformable sheet model. This single parameter control of scale makes it possible to perform scale space tracking by solving the differential equation that describes the trajectory of energy minima through scale space. Further, it permits adaptive scale step size selection based on the local properties of scale space, which allows for much larger steps than would be possible with the conservative step size required by nonadaptive techniques. We show that this process is characterized by a sparse linear system and prove that the associated matrix is positive definite and, consequently, nonsingular. Our analysis also provides for the determination of scale-dependent parameters, which is useful for efficient multiresolution processing. We have applied the deformable sheet model described to different problems in computational vision using real imagery with encouraging results, which are presented here.

Abstract:   The representation of shape in machine vision is reviewed with emphasis on the most common types of representation and recent developments. Both planar shape and solid shape are examined with connections and generalizations drawn wherever possible. Particular emphasis is placed on the importance of invariant descriptions and on the representation of shape classes.

Abstract:   In this paper, we present a new method for describing the shape of structures in grey-scale images, which is known as the intensity axis of symmetry (IAS). We describe the spatial and intensity variations of the image simultaneously rather than by the usual two-step process of 1) using intensity properties of the image to segment an image into regions and 2) describing the spatial shape of these regions. The result is an image shape description that is useful for a number of computer vision applications. Our method for computing this image shape description relies on minimizing an active surface functional that provides coherence in both the spatial and intensity dimensions while deforming into an axis of symmetry. Shape- based image segmentation is possible by identifying image regions associated with individual components of the IAS. The resulting image regions have geometric coherence and correspond well to visually meaningful objects in medical images.

Abstract:   Echocardiography has been widely used as a real-time non- invasive clinical tool to diagnose cardiac functions. Due to the poor quality and inherent ambiguity in echocardiograms, it is difficult to detect the myocardial boundaries of the left ventricle. Many existing methods are semi-automatic and detect cardial boundaries by serial computation which is too slow to be practical in real applications. In this paper, a new method for detecting the endocardial boundary by using a Hopfield neural network is proposed. Taking advantage of parallel computation and energy convergence capability in the Hopfield network, this method is faster and more stable for the detection of the endocardial border. Moreover, neither manual operations nor a priori assumptions are needed in this method. Experiments on several LV echocardiograms and clinical validation have shown the effectiveness of our method in these patient studies.

Abstract:   This article presents: (i) a multiscale representation of grey- level shape called the scale-space primal sketch, which makes explicit both features in scale-space and the relations between structures at different scales, (ii) a methodology for extracting significant blob-like image structures from this representation, and (iii) applications to edge detection, histogram analysis, and junction classification demonstrating how the proposed method can be used for guiding later-stage visual processes. The representation gives a qualitative description of image structure, which allows for detection of stable scales and associated regions of interest in a solely bottom-up data-driven way. In other words, it generates coarse segmentation cues, and can hence be seen as preceding further processing, which can then be properly tuned. It is argued that once such information is available, many other processing tasks can become much simpler. Experiments on real imagery demonstrate that the proposed theory gives intuitive results.

Abstract:   The use of energy-minimizing curves, known as ''snakes'' to extract features of interest in images has been introduced by Kass, Witkin and Terzopoulos [23]. A balloon model was introduced in [12] as a way to generalize and solve some of the problems encountered with the original method. A 3-D generalization of the balloon model as a 3-D deformable surface, which evolves in 3-D images, is presented. It is deformed under the action of internal and external forces attracting the surface toward detected edgels by means of an attraction potential. We also show properties of energy- minimizing surfaces concerning their relationship with 3-D edge points. To solve the minimization problem for a surface, two simplified approaches are shown first, defining a 3-D surface as a series of 2-D planar curves. Then, after comparing finite- element method and finite-difference method in the 2-D problem, we solve the 3-D model using the finite-element method yielding greater stability and faster convergence. This model is applied for segmenting magnetic resonance images.

Abstract:   Active contour models (snakes) are commonly used for locating the boundary of an object in computer vision applications. The minimisation procedure is the key problem to solve in the technique of active contour models. In this paper, a minimisation method for an active contour model using Hopfield networks is proposed. Due to its network structure, it lends itself admirably to parallel implementation and is potentially faster than conventional methods. In addition, it retains the stability of the snake model and the possibility for inclusion of hard constraints. Experimental results are given to demonstrate the feasibility of the proposed method in applications of industrial pattern recognition and medical image processing.

Abstract:   An interactive computer system has been developed for evaluating cytologic features derived directly from a digital scan of breast fine needle aspirate slides. The system uses computer vision techniques to analyze cell nuclei and classifies them using an inductive method based on linear programming. A digital scan of selected areas of the aspirate slide is done by a trained observer, while the analysis of the digitized image is done by an untrained observer. When trained and tested on 119 breast fine needle aspirates (68 benign and 51 malignant) using leave-one-out testing, 90% correctness was achieved. These results indicate that the method is accurate (good intraobserver and interobserver reproducibility) and that an untrained operator can obtain diagnostic results comparable to those achieved visually by experienced observers.

Abstract:   Most object recognition systems can only model objects composed of rigid pieces whose appearance depends only on lighting and viewpoint. Many real world objects, however, have variable appearances because they are flexible and/or have a variable number of parts. These objects cannot be easily modeled using current techniques. We propose the use of a knowledge representation called the VAPOR (Variable APpearance Object Representation) model to represent objects with these kinds of variable appearances. The VAPOR model is an idealization of the object; all instances of the model in an image are variations from the ideal appearance. The variations are evaluated by the description length of the data given the model, i.e., the number of information-theoretic bits needed to represent the model and the deviations of the data from the ideal appearance. The shortest length model is chosen as the best description. We demonstrate how the VAPOR model performs in a simple domain of circles and polygons and in the complex domain of finding cloverleaf interchanges in aerial images of roads.

Abstract:   In many applications of image analysis, simply connected objects are to be located in noisy images. During the last 5-6 years active contour models have become popular for finding the contours of such objects. Connected to these models are iterative algorithms for finding the minimizing energy curves making the curves behave dynamically through the iterations. These approaches do however have several disadvantages. The numerical algorithms that are in use constraint the models that can be used. Furthermore, in many cases only local minima can be achieved. In this paper, we discuss a method for curve detection based on a fully Bayesian approach. A model for image contours which allows the number of nodes on the contours to vary is introduced. Iterative algorithms based on stochastic sampling is constructed, which make it possible to simulate samples from the posterior distribution, making estimates and uncertainty measures of specific quantities available. Further, simulated annealing schemes making the curve move dynamically towards the global minimum energy configuration are presented. In theory, no restrictions on the models are made. In practice, however, computational aspects must be taken into consideration when choosing the models. Much more general models than the one used for active contours may however be applied. The approach is applied to ultrasound images of the left ventricle and to Magnetic Resonance images of the human brain, and show promising results.

Abstract:   Registering volumes that have been deformed with respect to each other involves recovery of the deformation. A 3-D elastic matching algorithm has been developed to use surface information for registering volumes. Surface extraction is performed in two steps: extraction of contours in 2-D image planes using active contours, and forming triangular patch surface models from the stack of 2-D contours. One volume is modeled as being deformed with respect to another goal volume. Correspondences between surfaces in the two image volumes are used to warp the deformed volume towards its goal. This process of contour extraction, surface formation and matching, and warping is repeated a number of times, with decreasing image volume stiffness. As the iterations continue the stretched volume is refined towards its goal volume. Registration examples of deformed volumes are presented.

Abstract:   This paper introduces a representation scheme for image sequences using nonuniform samples embedded in a deformable mesh structure. It describes a sequence by nodal positions and colors in a starting frame, followed by nodal displacements in the following frames. The nodal points in the mesh are more densely distributed in regions containing interesting features such as edges and corners; and are dynamically updated to follow the same features in successive frames. They are determined automatically by maximizing feature (e.g, gradient) magnitudes at nodal points, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. In order to avoid the mesh elements becoming overly deformed, a penalty term is also incorporated, which measures the irregularity of the mesh structure. The notions of shape functions and master elements commonly used in the finite element method have been applied to simplify the numerical calculation of the energy functions and their gradients. The proposed representation is motivated by the active contour or snake model proposed by Kass, Witkin, and Terzopoulos. The current representation retains the salient merit of the original model as a feature tracker based on local and collective information, while facilitating more accurate image interpolation and prediction. Our computer simulations have shown that the proposed scheme can successfully track facial feature movements in head-and-shoulder type of sequences, and more generally, interframe changes that can be modeled as elastic deformation. The treatment for the starting frame also constitutes an efficient representation of arbitrary still images.

Abstract:   A new approach is described for reconstructing coronary arteries from two sequences of projection images. The estimation of motion is performed on three-dimensional line segments (or centrelines), and is based on a 'prediction-projection-optimization' loop. The method copes with time varying properties, deformations and superpositions of vessels. Experiments using simulated and real data have been carried out, and the results found to be robust over a full cycle of a human heart. Local and global kinetic features can then be derived to obtain a greater insight on the cardiac functional state

Abstract:   Food material shape is often closely related to its qualify. Due to the demands of high quality, automated food shape inspection has become an important need for the food industry. Currently, accuracy and speed are two major problems for food shape inspection with computer vision. Therefore, in this study, a fast and accurate computer-vision based feature extraction and classification system was developed. In the feature extraction stage, a statistical model based feature extractor (SMB) and a multi-index active model-based (MAM) feature extractor were developed to improve the accuracy of classifications. In the classification stage, first the back-propagation neural network was applied as a multi-index classifier. Then, to speed up training, some minimum indeterminate zone (MIZ) classifiers were developed. Corn kernels, almonds, and animal-shaped crackers were used to rest the above techniques. The results showed that accuracy and speed were greatly improved when the MAM feature extractor was used in conjunction with the MIZ classifier.

Abstract:   Active contours, known as snakes, have found wide applications since their first introduction in 1987 by Kass et al. (Int. J. Comput. Vision 1, 321-331). However, one problem with the current models is that the performance depends on proper internal parameters and initial contour position, which, unfortunately, cannot be determined a priori. It is usually a hard job to tune internal parameters and initial contour position. The problem comes from the fact that the internal normal force at each point of contour is also a function of contour shape. To solve this problem, we propose to compensate for this internal normal force so as to make it independent of shape. As a result, the new model works robustly with no necessity to fine-tune internal parameters, and can converge to high curvature points like corners.

Abstract:   Neuroscientists have studied the relationship between nerve cell morphology and function for over a century. To pursue these studies, they need accurate three-dimensional models of nerve cells that facilitate detailed anatomical measurement and the identification of internal structures. Although serial transmission electron microscopy has been a source of such models since the mid 1960s, model reconstruction and analysis remain very time consuming. We have developed a new approach to reconstructing and visualizing 3D nerve cell models from serial microscopy. An interactive system exploits recent computer graphics and computer vision techniques to significantly reduce the time required to build such models. The key ingredients of the system are a digital ''blink comparator'' for section registration, ''snakes,'' or active deformable contours, for semiautomated cell segmentation, and voxel-based techniques for 3D reconstruction and visualization of complex cell volumes with internal structures.

Abstract:   This paper presents a method, based on the Filtered Backprojection technique (FBP), to extract directly the boundaries of X-ray images, without previous image reconstruction. We preprocess the raw data in order to compute directly the reconstructed values of the gradient or of the Laplacian at any location in the plane (defined with real coordinates). The reconstructed value of the gradient and of the Laplacian correspond to the exact mathematical definition of the differentials of the image. For noisy data, we propose also to use an extension of existing FBP techniques, adapted to the computation of the gradient and of the Laplacian. Finally, we show how to use the corresponding operators to perform the segmentation of a slice, without image reconstruction. Images of the reconstructed gradient, Laplacian, and segmented objects are presented.

Abstract:   A model for fusing the output of multiple segmentation modules is presented. The model is based on the particle system approach to modeling dynamic objects from computer graphics. The model also has built-in capabilities to extract regions, thin the edge image, remove ''twigs,'' and close gaps in the contours. The model functions both as an effective data fusion technique and as a model of an important human visual process. (C) 1994 Academic Press, Inc.

Abstract:   A new method to make an automatic initial estimation of the position of the middle of the left ventricular (LV) myocardial wall (LV myocardial midwall) in emission tomograms is presented. This method eliminates the manual interaction still required by other, more accurate LV delineation algorithms, and which consists of indicating the LV long axis and/or the LV extremities. A well-known algorithm from the world of neural networks, Kohonen's self-organizing maps, was adapted to use general shapes and to behave well for data with large background noise.

Abstract:   The variational method has been introduced by Kass et al. (1987) in the field of object contour modeling, as an alternative to the more traditional edge detection-edge thinning-edge sorting sequence. Since the method is based on a pre-processing of the image to yield an edge map, it shares the limitations of the edge detectors it uses. In this paper, we propose a modified variational scheme for contour modeling, which uses no edge detection step, but local computations instead-only around contour neighborhoods-as well as an ''anticipating'' strategy that enhances the modeling activity of deformable contour curves. Many of the concepts used were originally introduced to study the local structure of discontinuity, in a theoretical and formal statement by Leclerc & Zucker (1987), but never in a practical situation such as this one. The first part of the paper introduces a region-based energy criterion for active contours, and gives an examination of its implications, as compared to the gradient edge map energy of snakes. Then, a simplified optimization scheme is presented, accounting for internal and external energy in separate steps. This leads to a complete treatment, which is described in the last sections of the paper (4 and 5). The optimization technique used here is mostly heuristic, and is thus presented without a formal proof, but is believed to fill a gap between snakes and other useful image representations, such as split-and-merge regions or mixed line-labels image fields.

Abstract:   This paper presents an integrated approach to recovering the superquadric primitive from stereo images. While the depth data obtained from stereo matching algorithms are always sparse and noisy, to extract an object from the scene and obtain a smoothed depth map of the object, occluding contour detection and surface reconstruction are incorporated into the recovery process of superquadrics. The algorithm combines the recovery processes of occluding contour, surface and volumetric models in a cooperative and synergetic manner. The performance of the algorithm is demonstrated with two examples using real images.

Abstract:   Background Myocardial tissue tagging with the use of magnetic resonance imaging allows noninvasive regional analysis of heart wall motion and deformation. However, any evaluation of the effect of disease or treatment requires a baseline reference of normal values and variation. We studied the two-dimensional motion of material points imaged within the left ventricular wall using spatial modulation of magnetization (SPAMM) in 12 normal human volunteers. Methods and Results Five parallel short-axis and five parallel long-axis slices were acquired at five times during systole. SPAMM tags were generated at end diastole using a 7-mm grid. Intersection point data were analyzed for displacement, rotation, and torsion, and triangles of points were analyzed for local rotation and principal strains. Short-axis displacement was the least in the septum for all longitudinal levels (P<.001). Torsion about the long axis was uniform circumferentially because of the motion of the centroids used to reference the rotation. In the long-axis images, the base displaced longitudinally toward the apex, with the posterior wall moving farther than the anterior wall (13.4+/-2.2 versus 9.7+/-1.8 mm, P<.001) in this direction. The largest principal strain (maximum lengthening) was approximately radially oriented in both views. In the short-axis images, the minimum principal strain (maximum shortening) increased in magnitude toward the apex (P<.001) with little circumferential variation, except at midventricle, where the anterior wall showed greater contraction than the posterior wall (-0.21+/-0.03 versus -0.19+/-0.02, P<.02). Conclusions Consistent regional variations in deformation are seen in the normal human heart, Displacement and maximum shortening strains are well characterized with two-dimensional magnetic resonance tagging; however, higher-resolution images will be required to study transmural variations.

Abstract:   Most segmentation algorithms are composed of several procedures: split and merge, small region elimination, boundary smoothing,..., each depending on several parameters. The introduction of an energy to minimize leads to a drastic reduction of these parameters. The authors prove that the most simple segmentation tool, the ''region merging'' algorithm, made according to the simplest energy, is enough to compute a local energy minimum belonging to a compact class and to achieve the job of most of the tools mentioned above. The authors explain why ''merging'' in a variational framework leads to a fast multiscale, multichannel algorithm, with a pyramidal structure. The obtained algorithm is O(n ln n), where n is the number of pixels of the picture. This fast algorithm is applied to make grey level and texture segmentation and experimental results are shown.

Abstract:   A multiresolution approach to curve extraction in images is described. Based on a piecewise linear representation of curves, the scheme combines an efficient method of extracting line segments with a grouping process to identify curve traces. The line segments correspond to linear features defined at appropriate spatial resolutions within a quadtree structure and are extracted using a hierarchical decision process based on frequency domain properties. Implementation is achieved through the use of the multiresolution Fourier transform, a linear transform providing spatially localized estimates of the frequency spectrum over multiple scales. The scheme is simple to implement and computationally inexpensive, and results of experiments performed on natural images demonstrate that its performance compares favorably with that of existing methods. (C) 1994 Academic Press, Inc.

Abstract:   A method is described for extracting lineal features from an image using extended local information to provide robustness and sensitivity. The method utilizes both gradient magnitude and direction information, and incorporates explicit lineal and end-stop terms. These terms are combined nonlinearly to produce an energy landscape in which local minima correspond to lineal features called sticks that can be represented as line segments. A hill climbing (stick-growing) process is used to find these minima. The method is compared to two others, and found to have improved gap-crossing characteristics.

Abstract:   We propose an optimization approach to the estimation of a simple closed curve describing the boundary of an object represented in an image. The problem arises in a variety of applications, such as template matching schemes for medical image registration. A regularized optimization formulation with an objective function that measures the normalized image contrast between the inside and outside of a boundary is proposed. Numerical methods are developed to implement the approach, and a set of simulation studies are carried out to quantify statistical performance characteristics. One set of simulations models emission computed tomography (ECT) images; a second set considers images with a locally coherent noise pattern. In both cases, the error characteristics are found to be quite encouraging. The approach is highly automated, which offers some practical advantages over currently used technologies in the medical imaging field.

Abstract:   In this paper, we present a new approach for the automatic tracking of SPAMM (Spatial Modulation of Magnetization) grid in cardiac MR images and consequent estimation of deformation parameters. The tracking is utilized to extract grid points from MR images and to establish correspondences between grid points in images taken at consecutive frames. These correspondences are used with a thin plate spline model to establish a mapping from one image to the next. This mapping is then used for motion and deformation estimation. Spatio-temporal tracking of SPAMM grid is achieved by using snakes-active contour models with an associated energy functional. We present a minimizing strategy which is suitable for tracking the SPAMM grid. By continuously minimizing their energy functionals, the snakes lock on to and follow the in-slice motion and deformation of the SPAMM grid. The proposed algorithm was tested with excellent results on 123 images (three data sets each a multiple slice 2D, 16 phase Cine study, three data sets each a multiple slice 2D, 13 phase Cine study and three data sets each a multiple slice 2D, 12 phase Cine study).

Abstract:   Point displacement constraints constitute an attractive technique for interactive design of smooth curves, surfaces, and volumes. The user defines an arbitrary number of ''control points'' on the object and specifies their desired spatial location, while the system computes the object's degrees of freedom so that the constraints are satisfied. A constraint-based interface gives a feeling of direct manipulation of the object. In this article we introduce soft constraints, constraints which do not have to be met exactly. The softness of each constraint serves as a nonisotropic, local shape parameter enabling the user to explore the space of objects conforming to the constraints. Additionally, there is a global shape parameter which determines the amount of similarity of the designed object to a rest shape, or equivalently, the rigidity of the rest shape. We present an algorithm termed probabilistic point constraints (PPC) for implementing soft constraints. The PPC algorithm views constraints as stochastic measurements of the state of a static system. The softness of a constraint is derived from the covariance of the ''measurement.'' The resulting system of probabilistic equations is solved using the Kalman filter, a powerful estimation tool in the theory of stochastic systems. We also describe a user interface using direct-manipulation devices for specifying and visualizing covariances in 2D and 3D. The algorithm is suitable for any object represented as a parametric blend of control points, including most spline representations. The covariance of a constraint provides a continuous transition from exact interpolation to controlled approximation of the constraint. The algorithm involves only linear operations and allows real-time interactive direct manipulation of curves and surfaces on current workstations.

Abstract:   Image warping, often referred to as ''rubber sheeting,'' represents the deformation of a domain image space into a range image space. In this paper, a technique which extends the definition of a rubber-sheet transformation to allow a polygonal region to be warped into one or more subsets of itself, where the subsets may be multiply connected, is described. To do this, it constructs a set of ''slits'' in the domain image, which correspond to discontinuities and concavities in the range image, using a technique based on generalized Voronoi diagrams. The concept of medial axis is extended to describe inner and outer medial contours of a polygon. Polygonal regions are decomposed into annular subregions, and path homotopies are introduced to describe the annular subregions. These constructions motivate the definition of a ladder, which guides the construction of grid point pairs necessary to effect the warp itself. (C) 1994 Academic Press, Inc.

Abstract:   Image warping, often referred to as ''rubber sheeting,'' represents the deformation of a domain image space into a range image space. In this paper, a technique which extends the definition of a rubber-sheet transformation to allow a polygonal region to be warped into one or more subsets of itself, where the subsets may be multiply connected, is described. To do this, it constructs a set of ''slits'' in the domain image, which correspond to discontinuities and concavities in the range image, using a technique based on generalized Voronoi diagrams. The concept of medial axis is extended to describe inner and outer medial contours of a polygon. Polygonal regions are decomposed into annular subregions, and path homotopies are introduced to describe the annular subregions. These constructions motivate the definition of a ladder, which guides the construction of grid point pairs necessary to effect the warp itself. (C) 1994 Academic Press, Inc.

Abstract:   Reliable derivatives or digital images have always been hard to obtain, especially (but not only) at high orders. We analyze the sources of errors in traditional filters, such as derivatives or the Gaussian, that are used for differentiation. We then study a class of filters which is much more suitable for our purpose, namely filters that preserve polynomials up to a given order. We show that the errors in differentiation can be corrected using these filters. We derive a condition for the validity domain of these filters, involving some characteristics of the filter and of the shape. Our experiments show a very good performance for smooth functions.

Abstract:   Background In hypertrophic cardiomyopathy, ejection fraction is normal or increased, and force-length relations are reduced. However, three-dimensional (3D) motion and deformation in vivo have not been assessed in this condition. We have reconstructed the 3D motion of the left ventricle (LV) during systole in 7 patients with hypertrophic cardiomyopathy (HCM) and 12 normal volunteers by use of magnetic resonance tagging. Methods and Results Transmural tagging stripes were automatically tracked to subpixel resolution with an active contour model. A 3D finite-element model was used to interpolate displacement information between short- and long-axis slices and register data on a regional basis. Displacement and strain data were averaged into septal, posterior, lateral, and anterior regions at basal, midventricular, and apical levels. Radial motion (toward the central long axis) decreased slightly in patients with HCM, whereas longitudinal displacement (parallel to the long axis) of the base toward the apex was markedly reduced: 7.5 +/- 2.5 mm (SD) versus 12.5 +/- 2.0 mm, P<.001. Circumferential and longitudinal shortening were both reduced in the septum (P<.01 at all levels). The principal strain associated with 3D maximal contraction was slightly depressed in many regions, significantly in the basal septum (-0.18 +/- 0.05 versus -0.22 +/- 0.02, P<.05) walls. In contrast, LV torsion (twist of the apex about the long axis relative to the base) was greater in HCM patients (19.9 +/- 2.4 degrees versus 14.6 +/- 2.7 degrees, P<.01). Conclusions HCM patients had reduced 3D myocardial shortening on a regional basis; however, LV torsion was increased.

Abstract:   This paper considers the approach to dynamic image processing, which is one of the important problems in the future medical image processing. The tracking of the object and the analysis of the motion are discussed for the dynamic images of a nonrigid object with smooth shape, motion and deformation, which is the case in most medical images. This approach is based on an active contour model defined by an energy function in terms of both intra- and interframe constraints for the contour of the object. The contour of the target object is extracted and tracked by minimizing the energy function using multiscale dynamic programming and the motion is analyzed. The dynamic programming in multiscale proposed in this paper is to adjust the search neighborhood of the dynamic programming according to the scale. The coarse or fine neighborhood is defined for the coarse and fine scales, respectively, and the energy is minimized starting from the coarse scale and shifting to the fine scale. By this scheme, a large motion an deformation of the object can be handled. The proposed motion tracking method has been applied successfully to the dynamic image in the ''behavioral analysis of a slug aiming at the analysis of the neural mechanism of learning and memory formation in slugs,'' as well as to dynamic echocardiographic images. In the first application, the positive maximum of the curvature along the contour is extracted in the motion analysis as a characteristic point invariant to the deformation of the object. Then the shift of that point is traced. By this approach, the rough motion of the object can be estimated.

Abstract:   This paper proposes a robust method for tracking an object contour in a sequence of images. In this method, both object extraction and tracking problems can be solved simultaneously. Furthermore, it is applicable to the tracking of arbitrary shapes since it does not need a priori knowledge about the object shapes. In the contour tracking, energy-minimizing elastic contour models are utilized, which is newly presented in this paper. The contour tracking is formulated as an optimization problem to find the position that minimizes both the elastic energy of its model and the potential energy derived from the edge potential image that includes a target object contour. We also present an algorithm which efficiently solves energy minimization problems within a dynamic programming framework. The algorithm enables us to obtain optimal solution even when the variables to be optimized are not ordered. We show the validity and usefulness of the proposed method with some experimental results.

Abstract:   Our goal is to reconstruct both the shape and reflectance properties of surfaces from multiple images. We argue that an object-centered representation is most appropriate for this purpose because it naturally accommodates multiple sources of data, multiple images (including motion sequences of a rigid object), and self-occlusions. We then present a specific object-centered reconstruction method and its implementation. The method begins with an initial estimate of surface shape provided, for example, by triangulating the result of conventional stereo. The surface shape and reflectance properties are then iteratively adjusted to minimize an objective function that combines information from multiple input images. The objective function is a weighted sum of stereo, shading, and smoothness components, where the weight varies over the surface. For example, the stereo component is weighted more strongly where the surface projects onto highly textured areas in the images, and less strongly otherwise. Thus, each component has its greatest influence where its accuracy is likely to be greatest. Experimental results on both synthetic and real images are presented.

Abstract:   This paper presents a new method that combines a medial axis and implicit surfaces in order to reconstruct a 3D solid from on unstructured set of points scattered on the object's surface. The representation produced is based on iso-surfaces generated by skeletons, and is a particularly compact way of defining a smooth free-form solid. The method is based on the minimisation of an energy representing a ''distance'' between the set of data points and the iso-surface, resembling previous reserach(19). Initialisation, however, is more robust and efficient since there is computation of the medial axis of the set of points. Instead of subdividing existing skeletons in order to refine the object's surface, a new reconstruction algorithm progressively selects skeleton-points from the precomputed medial axis using an heuristic principle based on a ''local energy'' criterion. This drastically speeds up the reconstruction process. Moreover, using the medial axis allows reconstruction of objects with complex topology and geometry, like objects that have holes and branches or that are composed of several connected components. This process is fully automatic. The method has been successfully applied to both synthetic and real data.

Abstract:   Modeling a curve through minimizing its energy yields an overall smooth curve. A common way to model shape features is to perform the minimization subject to a number of interpolation constraints. This way of modeling is attractive because the designer is not bothered with the precise representation of the curve (e.g, control points). However, local shape specification by means of interpolation constraints is very limited. On the other hand, local deformation by repositioning control points is powerful but very laborious, and destroys the minimal energy property. In this paper, deform operators are introduced for 3D curve modeling that have built-in energy terms that have an intuitive effect. These operators allow local shape modification and do justice to the energy minimization way of modeling.

Abstract:   We present a graphically interactive procedure which is used to register a digital anatomic brain atlas with the tomographic patient volume. Patient structures to be segmented are outlined by local elastic deformation of corresponding objects from the anatomy model. This is performed in voxel space using a cost minimization procedure. The anatomic knowledge acquired in this manner is stored in a patient specific volume dataset and guides a raycaster with respect to the localization of object surfaces in order to control the result of the deformation process. Thus objects, which so far could not have been segmented appropriately or only after tedious manual editing efforts, become accessible by physicians. We present several results demonstrating the high quality and practicality of the method.

Abstract:   One approach to the detection of curves at subpixel accuracy involves the reconstruction of such features from subpixel edge data points. A new technique is presented for reconstructing and segmenting curves with subpixel accuracy using deformable models. A curve is represented as a set of interconnected Hermite splines forming a snake generated from the subpixel edge information that minimises the global energy functional integral over the set. While previous work on the minimisation was mostly based on the Euler-Lagrange transformation, the authors use the finite element method to solve the energy minimisation equation. The advantages of this approach over the Euler-Lagrange transformation approach are that the method is straightforward, leads to positive m-diagonal symmetric matrices, and has the ability to cope with irregular geometries such as junctions and corners. The energy functional integral solved using this method can also be used to segment the features by searching for the location of the maxima of the first derivative of the energy over the elementary curve set.

Abstract:   To provide an overview of the methods and clinical applications of three dimensional (3D) medical imaging in the oncologic patient. Methods and Materials: We briefly outline the techniques currently used to create 3D medical images with an emphasis on their strengths and shortcomings as they relate to oncologic imaging and radiation therapy planning, We then discuss some of the most important and promising oncologic applications of 3D imaging and suggest likely future directions in this rapidly developing field. Results: Since the first application of 3D techniques to medical data over a decade ago, 3D medical images have evolved from relatively crude representations of musculoskeletal abnormalities to detailed and accurate representations of a variety of soft tissue, vascular, and oncologic pathology. The rapid development of both computer hardware and software coupled with the application of 3D techniques to a variety of imaging modalities have expanded the clinical applications of this technology dramatically. Conclusions: 3D medical images are clinically practical tools for oncologic evaluation and effective radiation therapy planning.

Abstract:   The main aim of this work is the development of a vision-based road detection system fast enough to cope with the difficult real-time constraints imposed by moving vehicle applications. The hardware platform, a special-purpose massively parallel system, has been chosen to minimize system production and operational costs. This paper presents a novel approach to expectation-driven low-level image segmentation, which can be mapped naturally onto mesh-connected massively parallel SIMD architectures capable of handling hierarchical data structures. The input image is assumed to contain a distorted version of a given template; a multiresolution stretching process is used to reshape the original template in accordance with the acquired image content, minimizing a potential function. The distorted template is the process output.

Abstract:   Tissue tagging using magnetic resonance (MR) imaging has enabled quantitative noninvasive analysis of motion and deformation in vivo. One method for MR tissue tagging is Spatial Modulation of Magnetization (SPAMM), Manual detection and tracking of tissue tags by visual inspection remains a time-consuming and tedious process. We have developed an interactively guided semi-automated method of detecting and tracking tag intersections in cardiac MR images, A template matching approach combined with a novel adaptation of active contour modeling permits rapid analysis of MR images. We have validated our technique using MR SPAMM images of a silicone gel phantom with controlled deformations. Average discrepancy between theoretically predicted and semi-automatically selected tag intersections was 0.30 mm +/- 0.17 [mean +/- SD, NS (P < 0.05)]. Cardiac SPAMM images of normal volunteers and diseased patients also have been evaluated using our technique.

Abstract:   Point distribution models allow a compact description of an object's shape to be found from a set of example images. In previous work by the first author, a method of incorporating grey level information into a PDM was developed. This paper investigates fitting such a composite model to image data consisting of a set of images of a pig viewed from above. Model fitting is achieved by optimizing an objective function consisting of two components, one that measures the degree of grey level correspondence between the model and the data, and the other that measures how well the boundary of the model fits the data. The shape of the objective function as the model parameters are varied is investigated, and an optimization strategy developed. The strategy is used to find a pig in a number of images with backgrounds of increasing complexity. The strategy performs well with both an uncluttered and a realistic background. The performance with a simulated noisy background is not so good when the boundary component is included in the objective function. This is a result of the boundary component being more sensitive to noise in the image. In this case, it is better to optimize with the grey level component alone. A problem is identified when the grey level distribution changes significantly as the pig moves under the light source. It is suggested that this could be overcome by including variations in grey level distribution as modes in the model.

Abstract:   Active contour models (''snakes'') are a powerful tool for deformable object tracking in moving images. But the existing snake models are not well-adapted for tracking corners and objects on a complex background. In this paper, we present a novel active contour model, the ''Adjustable Polygons'', which is a set of active segments that can fit any object shape (including corners). A new energy based on textural characteristics of objects is also proposed, in order to resolve conflict situations while tracking objects on multiple contour background.

Abstract:   A new active contour model for finding and mapping the outer cortex in brain images is developed, A cross-section of the brain cortex is modeled as a ribbon, and a constant speed mapping of its spine is sought. A variational formulation, an associated force balance condition, and a numerical approach are proposed to achieve this goal, The primary difference between this formulation and that of snakes is in the specification of the external force acting on the active contour. A study of the uniqueness and fidelity of solutions is made through convexity and frequency domain analyses, and a criterion for selection of the regularization coefficient is developed. Examples demonstrating the performance of this method on simulated and real data are provided.

Abstract:   To obtain a three-dimensional reconstruction of the hippocampus from a volumetric MRI head study, it is necessary to separate that structure not only from the surrounding white matter, but also from contiguous areas of gray matter-the amygdala and cerebral cortex. At present it is necessary for a physician to manually segment the hippocampus on each slice of the volume to obtain such a reconstruction. This process is time consuming, and is subject to inter- and intra-operator variation as well as large discontinuities between slices. We propose a novel technique, making use of a combination of gray scale and edge-detection algorithms and some a priori knowledge, by which a computer may make an unsupervised identification of a given structure through a series of contiguous images. This technique is applicable even if the structure includes so-called false contours or missing contours. Applications include three-dimensional reconstruction of difficult-to-segment regions of the brain, and volumetric measurements of structures from series of two-dimensional images.

Abstract:   Fine needle aspiration (FNA) accuracy is limited by, among other factors, the subjective interpretation of the aspirate. We have increased breast FNA accuracy by coupling digital image analysis methods with machine learning techniques. Additionally, our mathematical approach captures nuclear features (''grade'') that are prognostically more accurate than are estimates based on tumor size and lymph node status. An interactive computer system evaluates, diagnoses and determines prognosis based on nuclear features derived directly from a digital scan of FNA slides. A consecutive series of 569 patients provided the data for the diagnostic study. A 166-patient subset provided the data for the prognostic study. An additional 75 consecutive, new patients provided samples to test the diagnostic system. The projected prospective accuracy of the diagnostic system was estimated to be 97% by 10-fold cross-validation, and the actual accuracy on 75 new samples runs 100%. The projected prospective accuracy of the prognostic system was estimated to be 86% by leave-one-out testing.

Abstract:   We describe some of the current challenges in developing and validating computer vision algorithms for manufacturing applications. We focus on the general theme of template-based processing, where geometric templates provide a basis for local feature analysis, registration and recognition (via constraint-based modelling) and model adaptation using statistical methods. We describe recent successful applications of template-based techniques in the areas of manufacturing part inspection and process understanding and monitoring. We also examine the question 'Why are there so few computer vision applications in manufacturing?' We suggest that two of the major bottlenecks remain speed of algorithm development and how to validate algorithm performance with a limited data set. Finally, we identify some of what we see as emerging and future potential application areas of computer vision methods in manufacturing, where the current trend is to provide tools for continuous product improvement rather than (final) product inspection, and 3D measurement capabilities.

Abstract:   The goal of the described work is to model visual articulation movements of prototypic speakers with respect to custom-made text A language-wide extension of the motion model leads to a visible speech synthesis and further more to an artificial computer trainer for speechreading. The developed model is based on a set of specific video key-pictures and the interpolation of interim pictures. The key-picture selection is realized by a fuzzy-c-means classification algorithm.

Abstract:   The automated analysis of 3D medical images can improve both diagnosis and therapy significantly. This automation raises a number of new fascinating research problems in the fields of computer vision, graphics and robotics. In this paper, I propose a list of such problems after a review of the current major 3D imaging modalities, and a description of the related medical needs. I then present some of the past and current work done in our research group EPIDAURE* at INRIA, on the following topics: segmentation of 3D images; 3D shape modelling; 3D rigid and nonrigid registration; 3D motion analysis; and 3D simulation of therapy. Most topics are discussed in a synthetic manner, and illustrated by results. Rigid matching is treated more thoroughly as an illustration of a transfer from computer vision towards 3D image processing. The later topics are illustrated by preliminary results, and a number of promising research tracks are suggested.

Abstract:   We present a model-based method for object identification in images of natural scenes. It has successfully been implemented for the classification of cars based on their rear view. In a first step, characteristic features such as lines and corners are detected within the image. Generic models of object-classes, described by the same set of features, are stored in a database. Each model represents a whole class of objects (e.g., passenger cars, vans, big trucks). In a preprocessing stage, the most probable object is selected by means of a corner-feature based Hough transform. This transformation also suggests the position and scale of the object in the image. Guided by similarity measures, the model is then aligned with image features using a matching algorithm based on the elastic net technique [1]. During this iterative process, the model is allowed to undergo changes in scale, position and certain deformations. Deformations are kept within limits such that one model can fit to all objects belonging to the same class, but not to objects of other classes. In each iteration step, quantities to assess the matching process are obtained.

Abstract:   A two-stage algorithm for extraction of the ventricular chambers (endocardial surfaces) in flow-enhanced magnetic resonance images is described, In the first stage, the approximate locations and sizes of the endocardial surfaces are determined by intensity thresholding. In the second stage, points on each approximated surface are repositioned to nearest locally maximum gradient magnitude points and a generalized cylinder is fitted to them, Examples of ventricular chambers in cine MR images determined by this algorithm are presented.

Abstract:   When interpreting a dynamic and uncertain world it is important to have a high-level vision component that can guide the reasoning of the whole vision system. This guidance is provided by an attentional mechanism that exploits knowledge of the specific problem being solved. Here we survey work relevant to the development of such an attentional mechanism, using surveillance as an application domain to tie together issues of spatial representation, events, behaviour, control and planning. The paper culminates in a brief description of HIVIS-WATCHER a program that makes use of all these areas.

Abstract:   Modal matching is a new method for establishing correspondences and computing canonical descriptions, The method is based on the idea of describing objects in terms of generalized symmetries, as defined by each object's eigenmodes. The resulting modal description is used for object recognition and categorization, where shape similarities are expressed as the amounts of modal deformation energy needed to align the two objects, In general, modes provide a global-to-local ordering of shape deformation and thus allow for selecting which types of deformations are used in object alignment and comparison, In contrast to previous techniques, which required correspondence to be computed with an initial or prototype shape, modal matching utilizes a new type of finite element formulation that allows for an object's eigenmodes to be computed directly from available image information, This improved formulation provides greater generality and accuracy, and is applicable to data of any dimensionality, Correspondence results with 2D contour and point feature data are shown, and recognition experiments with 2D images of hand tools and airplanes are described.

Abstract:   Edge detection is formulated as a curve fitting problem. First, high-gradient pixels are grouped into elongated regions and then a curve is fitted to each. The curve fitting method used in this work does not require solving a system of equations, and therefore is fast. Examples of edge detection by curve fitting on synthetic and real images are presented, and results obtained are compared with those determined by the Laplacian of Gaussian operator.

Abstract:   Objective: To use digital image analysis and machine learning to (1) improve breast mass diagnosis based on fine-needle aspirates and (2) improve breast cancer prognostic estimations. Design: An interactive computer system evaluates, diagnoses, and determines prognosis based on cytologic features derived from a digital scan of fine-needle aspirate slides. Setting: The University of Wisconsin (Madison) Departments of Computer Science and Surgery and the University of Wisconsin Hospital and Clinics. Patients: Five hundred sixty-nine consecutive patients (212 with cancer and 357 with benign masses) provided the data for the diagnostic algorithm, and an additional 118 (31 with malignant masses and 87 with benign masses) consecutive, new patients tested the algorithm. One hundred ninety of these patients with invasive cancer and without distant metastases were used for prognosis. Interventions: Surgical biopsy specimens were taken from all cancers and some benign masses. The remaining cytologically benign masses were followed up for a year and surgical biopsy specimens were taken if they changed in size or character. Patients with cancer received standard treatment. Outcome Measures: Cross validation was used to project the accuracy of the diagnostic algorithm and to determine the importance of prognostic features. In addition, the mean errors were calculated between the actual times of distant disease occurrence and the times predicted using various prognostic features. Statistical analyses were also done. Results The predicted diagnostic accuracy was 97% and the actual diagnostic accuracy on 118 new samples was 100%. Tumor size and lymph node status were weak prognosticators compared with nuclear features, in particular those measuring nuclear size. Compared with the actual time for recurrence, the mean error of predicted times for recurrence with the nuclear features was 17.9 months and was 20.1 months with tumor size and lymph node status (P=.11). Conclusion: Computer technology will improve breast fine-needle aspirate accuracy and prognostic estimations.

Abstract:   This paper presents a new method to segment brain parenchyma and cerebrospinal fluid spaces automatically in routine axial spin echo multispectral MR images. The algorithm simultaneously incorporates information about anatomical boundaries (shape) and tissue signature (grey scale) using a priori knowledge. The head and brain are divided into four regions and seven different tissue types. Each tissue type c is modeled by a multivariate Gaussian distribution N(mu(c), Sigma(c)). Each region is associated with a finite mixture density corresponding to its constituent tissue types, Initial estimates of tissue parameters {mu(c), Sigma(c)}(c=1,...,7) are obtained from L-means clustering of a single slice used for training. The first algorithmic step uses the EM-algorithm for adjusting the initial tissue parameter estimates to the MR data of new patients, The second step uses a recently developed model of dynamic contours to detect three simply closed nonintersecting curves in the plane, constituting the arachnoid/dura mater boundary of the brain, the border between the subarachnoid space and brain parenchyma, and the inner border of the parenchyma toward the lateral ventricles, The model, which is formulated by energy functions in a Bayesian framework, incorporates a priori knowledge, smoothness constraints, and updated tissue type parameters, Satisfactory maximum a posteriori probability estimates of the closed contour curves defined by the model were found using simulated annealing.

Abstract:   Point distribution models (PDMs) allow a compact description of an object's shape to be found from a set of example images. In previous work by the second author a method of incorporating grey level information into a PDM was developed. Further work investigated fitting such a composite model to image data consisting of a set of images of a pig viewed from above. This paper describes work on images containing more than one pig. A technique for initialising the model is used which searches the image for ridges in the grey level landscape. These generally lie along the backbone of the animal and provide a good starting point for automatic fitting. By minimising an objective function which measures the difference in grey level and the error in boundary correspondence, an accurate fit of model to data is obtained. Ridge detection initialises the model to within +/-12 pixels of the object. Strict limits on the boundaries of the search space constrain the minimisation process allowing convergence to the true minimum. The resulting fit is good even for objects which are partially obscured. Poor final values of the objective function allow the detection of erroneous results.

Abstract:   In this paper, we attack the figure-ground discrimination problem from a combinatorial optimization perspective. In general, the solutions proposed in the past solved this problem only partially: either the mathematical model encoding the figure-ground problem was too simple or the optimization methods that were used were not efficient enough or they could not guarantee to find the global minimum of the cost function describing the figure-ground model. The method that we devised and which is described in this paper is tailored around the following contributions. First, we suggest a mathematical model encoding the figure-ground discrimination problem that makes explicit a definition of shape (or figure) based on cocircularity, smoothness, proximity, and contrast. This model consists of building a cost function on the basis of image element interactions. Moreover, this cost function fits the constraints of an interacting spin system, which in turn is a well suited physical model to solve hard combinatorial optimization problems. Second, we suggest a combinatorial optimization method for solving the figure-ground problem, namely mean field annealing which combines the mean field approximation and annealing. Mean field annealing may well be viewed as a deterministic approximation of stochastic methods such as simulated annealing. We describe in detail the theoretical bases of this method, derive a computational model, and provide a practical algorithm. Finally, some experimental results are shown for both synthetic and real images.

Abstract:   This paper describes several new image understanding methods based on parallel operation. There are several constraint satisfaction approaches using an energy minimization. We show how we reconstruct three-dimensional surfaces from contours without elevation data and sparse points of known elevation data using this approach. We also introduce Active Net using this approach, and apply this model to segmentation and binocular stereo matching. We experimented with these energy minimization approaches to solve the problems of early and intermediate levels of computer vision, and show some of the results of our recent research.

Abstract:   We propose an efficient method for tracking several objects moving through a sequence of monocular images against a non-uniform background. Each object entering the scene is intercepted by an active contour model which locks on it as long as it moves in the scene. The procedure does not necessitate an interactive initialization. Some results are presented in case of real traffic scenes.

Abstract:   In this paper, we present a system for detection and tracking of tubular molecules in images. The automatic detection and characterization of the shape, location, and motion of these molecules can enable new laboratory protocols in several scientific disciplines. The uniqueness of the proposed system is twofold: At the macro level, the novelty of the system lies in the integration of object localization and tracking using geometric properties; at the micro level, in the use of high and low level constraints to model the detection and tracking subsystem. The underlying philosophy for object detection is to extract perceptually significant features from the pixel level image, and then use these high level cues to refine the precise boundaries. In the case of tubular molecules, the perceptually significant features are antiparallel line segments or, equivalently, their axis of symmetries. The axis of symmetry infers a coarse description of the object in terms of a bounding polygon. The polygon then provides the necessary boundary condition for the refine ment process, which is based on dynamic programming. For tracking the object in a time sequence of images, the refined contour is then projected onto each consecutive frame.

Abstract:   A constrained variational curve is a curve that minimizes some energy functional under certain interpolation constraints. Modeling curves using constrained variational principles is attractive, because the designer is not bothered with the precise representation of the curve (e.g. control points). Until now, the modeling of variational curves is mainly done by means of constraints. If such a curve of least energy is deformed locally (e.g, by moving its control points) the concept of energy minimization is lost. In this paper we introduce deform operators with built-in energy terms. We have tested our ideas in a prototype system for modeling uniform B-spline curves. Through the use of widgets, the user can interactively modify the range of influence and other properties of the operators. Experiments show that these operators offer a very intuitive way of modeling.

Abstract:   This paper reports on current developments in the area of model-based video coding, a technique which shows promise of achieving very, large bit-rate reductions for moving images. After an introduction and historical review, advances are summarized in several areas, among them improved 3D tracking of the human head and of facial expressions, the use of muscle-driven model animation with skin synthesis, techniques for luminance compensation, and switched coders. Bit rates ranging from 64 kb/s down to about 1 kb/s have been obtained using head-and-shoulder video sequences. Problems with model-based methods are identified and future developments in both CBR and VER transmission discussed.

Abstract:   A method for the segmentation of complex, three-dimensional objects using hierarchical active surface templates is presented. The templates consist of one or more active surface models which are specified according to a priori knowledge about the expected shape and location of the desired object. This allows complex objects to be naturally modeled as collections of simple subparts which are geometrically constrained. The template is adaptively deformed by the three-dimensional image data in which it is initialized such that the template boundaries are brought into correspondence with the assumed image object. An external energy field is developed based on a vector distance transform such that the surfaces are deformed according to object shape. The method is demonstrated by the segmentation of the human brain from three-dimensional magnetic resonance images of the head given an a priori model of a normal brain.

Abstract:   Correspondence establishment has been a difficult problem in machine vision. In this paper, we present an optimization technique for the task. The geometric constraints to the solution are formulated as forces, which are combined to provide clue for mapping between two sets of points such that the geometric constraints are best satisfied. The strong point of this method is that it is easy to integrate several sources of information to obtain a solution while keeping the decision simple, and does not suffer from the uncontrollable flexibility as in active contour models. We illustrate the method with the problem of establishing correspondence between parallel curves.

Abstract:   We undertake to develop a general theory of two-dimensional shape by elucidating several principles which any such theory should meet. The principles are organized around two basic intuitions: first, if a boundary were changed only slightly, then, in general, its shape would change only slightly. This leads us to propose an operational theory of shape based on incremental contour deformations. The second intuition is that not all contours are shapes, but rather only those that can enclose ''physical'' material. A theory of contour deformation is derived from these principles, based on abstract conservation principles and Hamilton-Jacobi theory. These principles are based on the work of Sethian (1985a, c), the Osher-Sethian (1988), level set formulation the classical shock theory of Lax (1971; 1973), as well as curve evolution theory for a curve evolving as a function of the curvature and the relation to geometric smoothing of Gage-Hamilton-Grayson (1986; 1989). The result is a characterization of the computational elements of shape: deformations, parts, bends, and seeds, which show where to place the components of a shape. The theory unifies many of the diverse aspects of shapes, and leads to a space of shapes (the reaction/diffusion space), which places shapes within a neighborhood of ''similar'' ones. Such similarity relationships underlie descriptions suitable for recognition.

Abstract:   Visual assessments of nuclear grade are subjective yet still prognostically important. Now, computer-based analytical techniques can objectively and accurately measure size, shape and texture features, which constitute nuclear grade. The cell samples used in this study were obtained by fine needle aspiration (FNA) during the diagnosis of 187 consecutive patients with invasive breast cancer. Regions of FNA preparations to be analyzed were digitized and displayed on a computer monitor. Nuclei to be analyzed were roughly outlined by an operator using a mouse. Next, the computer generated a ''snake'' that precisely enclosed each designated nucleus. Ten nuclear features were then calculated for each nucleus based on these snakes. These results were analyzed statistically and by an inductive machine learning technique that we developed and call ''recurrence surface approximation'' (RSA). Both the statistical and RSA machine learning analyses demonstrated that computer-derived nuclear features are prognostically move important than are the classic prognostic features, tumor size and lymph node status.

Abstract:   It is generally agreed that individual visual cues are fallible and often ambiguous. This has generated a lot of interest in design of integrated vision systems which are expected to give a reliable performance in practical situations. The design of such systems is challenging since each vision module works under a different and possibly conflicting set of assumptions. We have proposed and implemented a multiresolution system which integrates perceptual organization (grouping), segmentation, stereo, shape from shading, and line labeling modules. We demonstrate the efficacy of our approach using images of several different realistic scenes. The output of the integrated system is shown to be insensitive to the constraints imposed by the individual modules. The numerical accuracy of the recovered depth is assessed in case of synthetically generated data. Finally, we have qualitatively evaluated our approach by reconstructing geons from the depth data obtained from the integrated system. These results indicate that integrated vision systems are likely to produce better reconstruction of the input scene than the individual modules.

Abstract:   Magnetic resonance tissue tagging allows noninvasive in vivo measurement of soft tissue deformation, Planes of magnetic saturation are created, orthogonal to the imaging plane, which form dark lines (stripes) in the image, We describe a method for tracking stripe motion in the image plane, and show how this information can be incorporated into a finite element model of the underlying deformation, Human heart data were acquired from several imaging planes in different orientations and were combined using a deformable model of the left ventricle wall, Each tracked stripe point provided information on displacement orthogonal to the original tagging plane, i.e., a one-dimensional (1-D) constraint on the motion, Three-dimensional (3-D) motion and deformation was then reconstructed by fitting the model to the data constraints by linear least squares, The average root mean squared (rms) error between tracked stripe points and predicted model locations was 0.47 mm (n = 3100 points). In order to validate this method and quantify the errors involved, we applied it to images of a silicone gel phantom subjected to a known, well-controlled, 3-D deformation. The finite element strains obtained were compared to an analytic model of the deformation known to be accurate in the central axial plane of the phantom, The average rms errors were 6% in both the reconstructed shear strains and 16% in the reconstructed radial normal strain.

Abstract:   This paper proposes a new approach for inputting handwritten Distribution Facility Drawings (DFD) and their maps into a computer automatically by using the Facility Management Database (FMD). Our recognition method makes use of external information for drawing/map recognition. It identifies each electric-pole symbol and support cable symbol on drawings simply by consulting the FMD. Other symbols such as transformers and electric wires can be placed on drawings automatically. In this positioning of graphic symbols, we present an automatic adjustment method of a symbol's position on the latest digital maps. When a contradiction is unsolved due to an inconsistency between the content of the DFD and the FMD, the system requests a manual feedback from the operator. Furthermore, it uses the distribution network of the DFD to recognize the street lines on the maps which aren't computerized. This can drastically reduce the cost for computerizing drawings and maps.

Abstract:   We present in this paper a new curve and surface implicit model. This implicit model is based on hyperquadrics and allows a local and global control of the shape and a wide variety of allowable shapes. We define a hybrid hyperquadric model by introducing implicitly some local properties on a global shape model. The advantage of our model is that it describes global and local properties through a unique implicit equation, yielding a representation of the shape by means of its parameters, independently of the chosen numerical resolution. The data fitting is obtained through the minimization of energy, modeling the attraction to data independently of the implicit description of the shape, After studying the geometry of hyperquadrics and how the shape deforms when we modify slightly its implicit equation, we are able to define an algorithm for automatic refining of the fit by adding an adequate term to the implicit representation, This geometric approach malt:es possible an efficient description of the data points and an automatic tuning of the fit according to the desired accuracy. (C) 1996 Academic Press, Inc.

Abstract:   This paper presents a new edge detection scheme that detects two-dimensional (2-D) edges by a curve-segment-based detection functional guided by the zero-crossing contours of the Laplacian-of-Gaussian (LOG) to approach the true edge locations. The detection functional is shown to be optimal in terms of signal-to-noise ratio (SNR) and edge localization accuracy; it also preserves the nice scaling property held uniquely by the LOG in scale space.

Abstract:   A unified framework for 3-D shape reconstruction allows us to combine image-based and geometry-based information sources. The image information is akin to stereo and shape-from-shading, while the geometric information may be provided in the form of 3-D points, 3-D features, or 2-D silhouettes. A formal integration framework is critical in recovering complicated surfaces because the information from a single source is often insufficient to provide a unique answer. Our approach to shape recovery is to deform a generic object-centered 3-D representation of the surface so as to minimize an objective function, This objective function is a weighted sum of the contributions of the various information sources. We describe these various terms individually, our weighting scheme, and our optimization method, Finally, we present results on a number of difficult images of real scenes for which a single source of information would have proved insufficient. (C) 1996 Academic Press, Inc.

Abstract:   The goal of this paper is to offer a structured synopsis of the problems in image motion computation and analysis, and of the methods proposed, exposing the underlying models and supporting assumptions. A sufficient number of pointers to the literature will be given, concentrating mostly on recent contributions. Emphasis will be on the detection, measurement and segmentation of image motion. Tracking, and deformable motion isssues will be also addressed. Finally, a number of related questions which could require more investigations will be presented.

Abstract:   Analysis of brain images often requires accurate localization of cortical convolutions. Although magnetic resonance (MR) brain images offer sufficient resolution for identifying convolutions in theory, the nature of tomographic imaging prevents clear definition of convolutions in individual slices, Existing methods for solving this problem rely on heuristic adaptation of brain atlases created from a small number of individuals, These methods do not usually provide high accuracy because of large biological variations among individuals. We propose to localize convolutions by linking realistic visualizations of the cortical surface with the original image volume. We have developed a system so that a user can quickly localize key convolutions in several visualizations of an entire brain surface, Because of the links between the visualizations and the original volume, these convolutions are simultaneously localized in the original image slices, In the process of our development, we have implemented a fast and easy method for visualizing cortical surfaces in MR images, thereby making our scheme usable in practical applications.

Abstract:   We have devised, implemented, and tested a fast, spatially accurate technique for calculating the high-dimensional deformation held relating the brain anatomies of an arbitrary pair of subjects, The resulting three-dimensional (3-D) deformation map can be used to quantify anatomic differences between subjects or within the same subject over time and to transfer functional information between subjects or integrate that information on a single anatomic template. The new procedure is based on developmental processes responsible for variations in normal human anatomy and is applicable to 3-D brain images in general, regardless of modality, Hybrid surface models known as Chen surfaces (based on superquadrics and spherical harmonics) are used to efficiently initialize 3-D active surfaces, and these then extract from both scans the developmentally fundamental surfaces of the ventricles and cortex. The construction of extremely complex surface deformation maps on the internal cortex is made easier by budding a generic surface structure to model it, Connected systems of parametric meshes model several deep sulci whose trajectories represent critical functional boundaries, These sulci are sufficiently extended inside the brain to reflect subtle and distributed variations in neuroanatomy between subjects. The algorithm then calculates the high-dimensional volumetric warp (typically with 384(2) x 256 x 3 approximate to 0.1 billion degrees of freedom) deforming one 3-D scan into structural correspondence with the other. Integral distortion functions are used to extend the deformation held required to elastically transform nested surfaces to their counterparts in the target scan. The algorithm's accuracy is tested, by warping 3-D magnetic resonance imaging (MRI) volumes from normal subjects and Alzheimer's patients, and by warping full-color 1024(3) digital cryosection volumes of the human head onto MRI volumes, Applications are discussed, including the transfer of multisubject 3-D functional, vascular, and histologic maps onto a single anatomic template; the mapping of 3-D brain atlases onto the scans of new subjects; and the rapid detection, quantification, and mapping of local shape changes in 3-D medical images in disease and during normal or abnormal growth and development.

Abstract:   We present a new mathematical formulation of some curve and surface reconstruction algorithms by the introduction of auxiliary variables. For deformable models and templates, the extraction of a shape is obtained through the minimization of an energy composed of an internal regularization term (not necessary in the case of parametric models) and an external attraction potential. Two-step iterative algorithms have been often used where, at each iteration, the model is first locally deformed according to the potential data attraction and then globally smoothed (or fitted in the parametric case). We show how these approaches can be interpreted as the introduction of auxiliary variables and the minimization of a two-variables energy. The first variable corresponds to the original model we are looking for, while the second variable represents an auxiliary shape close to the first one. This permits to transform an implicit data constraint defined by a non convex potential into an explicit convex reconstruction problem. This approach is much simpler since each iteration is composed of two simple to solve steps. Our formulation permits a more precise setting of parameters in the iterative scheme to ensure convergence to a minimum. We show some mathematical properties and results on this new auxiliary problem, in particular when the potential is a function of the distance to the closest feature point. We then illustrate our approach for some deformable models and templates.

Abstract:   Shape modeling is an important constituent of computer vision as well as computer graphics research. Shape models aid the tasks of object representation and recognition. This paper presents a new approach to shape modeling which retains some of the attractive features of existing methods, and overcomes some of their limitations. Our technique can be applied to model arbitrarily complex shapes, which include shapes with significant protrusions, and to situations where no a priori assumption about the object's topology is made. A single instance of our model, when presented with an image having more than one object of interest, has the ability to split freely to represent each object. This method is based on the ideas developed by Osher and Sethian to model propagating solid/liquid interfaces with curvature-dependent speeds. The interface (front) is a closed, nonintersecting, hypersurface flowing along its gradient field with constant speed or a speed that depends on the curvature. It is moved by solving a ''Hamilton-Jacobi'' type equation written for a function in which the interface is a particular level set. A speed term synthesized from the image is used to stop the interface in the vicinity of object boundaries. The resulting equation of motion is solved by employing entropy-satisfying upwind finite difference schemes. We also introduce a new algorithm for rapid advancement of the front using what we call a narrow-band update scheme. The efficacy of the scheme is demonstrated with numerical experiments on low contrast medical images.

Abstract:   A method is described for automatically tracking spatial modulation of magnetization tag lines on gated cardiac images. The method differs from previously reported methods in that it uses Fourier based spatial frequency and phase information to separately track horizontal and vertical tag lines. Use of global information from the frequency spectrum of an entire set of tag lines was hypothesized to result in a robust algorithm with decreased sensitivity to noise. The method was validated in several ways: first, actual tagged cardiac images at end diastole were deformed known amounts, and the algorithm's predictions compared to the known deformations. Second, tagged, gated images of the thigh muscle (assumed to have similar signal to noise characteristics as cardiac images, but to not deform with time) were created. Again the algorithmic predictions could be compared to the known (zero magnitude) deformations and to thigh images which had been artificially deformed. Finally, actual cardiac tagged images were acquired, and comparisons made between manual, visual, determinations of tag line locations, and those predicted by the algorithm. At 0.5 T, the mean bias of the method was <0.34 mm even at large deformations and at late (noisy) times. The standard deviation of the method, estimated from the tagged thigh images, was <0.7 mm even at late times. The method may be expected to have even lower error at higher field strengths.

Abstract:   A new method for the application of active contours to biomedical images is described. The new approach, which involves extensive modification of the internal energy function acid a different method of minimising the energy functional, yields rapid, excellent fits to MR images.

Abstract:   Rationale and Objectives. We designed an image processing technique to automatically measure the biparietal diameter (BPD) and head circumference (HC) from prenatal sonograms, We evaluated the performance of the algorithm by comparing the resulting measurements with those made by experienced sonographers. Methods. Thirty-five digitized sonograms of the fetal head were obtained during routine imaging, The BPD and HC were automatically computed by detecting the inner and outer boundaries of the fetal skull using the computer vision technique known as the ''active contour model.'' Six experienced sonographers also measured the BPD and HC on these images. Results. The algorithm failed to locate the boundaries in two of the 35 cases. For the remaining cases, the mean absolute difference betnieen the automated measurements and the average of the six observers was 1.4% for BPD and 2.9% for HC. The correlations were .999 for the BPD and .994 for the HC. The computer's measurements were no different from the six observers' measurements than the observers' measurements were from one another. Conclusion. The tested algorithm effectively and accurately measures BPD and HC automatically. We are currently in the process of integrating this algorithm into an ultrasound machine.

Abstract:   We present a principle of nonlinear superposition of receptive fields. Changes of connection weight, applied field or the distances between the input centers can lead to a new phase with all neurons encoding certain shapes excited. This process is a kind of phase transition and can be used for information processing.

Abstract:   A system has been developed that combines multiparameter fluorescence imaging and computer vision techniques to provide automatic phenotyping of multiple cell types in a single tissue section. This system identifies both the nuclear and cytoplasmic boundary of each cell. A routine based on the watershed algorithm has been developed to segment an image of Hoechst-stained nuclei with an accuracy of greater than 85%. Deformable splines initially positioned at the nuclear boundaries are applied to images of fluorescently labelled cell-surface antigens. The splines lock onto the peak fluorescence signal surrounding the cell, providing an estimate of the cell boundary. From measurements acquired at this boundary, each cell is classified according to antigen expression. The system has been piloted in biopsies from melanoma patients participating in a clinical trial of the antibody R(24). Thin tissue sections have been stained with Hoechst and three different fluorescent antibodies to antigens that permit the typing and evaluation of activity of T-cells. Changes in the infiltrates evaluated by multiparameter imaging were consistent with results obtained by immunoperoxidase analysis. The multiparameter fluorescent technique enables simultaneous determination of multiple cell subsets and can provide the spatial relationships of each cell type within the tissue. (C) 1996 Wiley-Liss, Inc.

Abstract:   Deformable models are a powerful and popular tool for image segmentation, but in 3D imaging applications the high computational cost of fitting such models can be a problem. A further drawback is the need to select the initial size and position of a model in such a way that it is close to the desired solution. This task may require particular expertise on the part of the operator, and, furthermore, may be difficult to accomplish in three dimensions without the use of sophisticated visualisation techniques. This article describes a 3D deformable model that uses an adaptive mesh to increase computational efficiency and accuracy. The model employs a distance transform in order to overcome some of the problems caused by inaccurate initialisation. The performance of the model is illustrated by its application to the task of segmentation of 3D MR images of the human head and hand. A quantitative analysis of the performance is also provided using a synthetic test image.

Abstract:   A new technique is presented for clump decomposition based on the recursive splitting of active contours. The approach does not require prior knowledge of tlx number of objects and the sizes of the objects to be segmented.

Abstract:   Many researchers have studied techniques related to the analysis and synthesis of human heads under motion with face deformations. These techniques can be used for defining low-rate Image compression algorithms (model-based image coding), cinema technologies, videophones, as well as for applications of virtual reality, etc. Such techniques need a real-time performance and a strong integration between the mechanisms of motion estimation and those of rendering and animation of the 3D synthetic head/face. In this paper, a complete and integrated system for tracking and synthesizing facial motions in real-time with low-cost architectures is presented. Facial deformations curves represented as spatiotemporal B-splines are used for tracking in order to model the main facial features. In addition, the system proposed is capable of adapting a generic 3D wire-frame model of a head/face to the face that must be tracked; therefore: the simulations of the face deformations are produced by using a realistic patterned face. (C) 1996 Academic Press Limited

Abstract:   Availability of Visible Human Dataset (VHD) has provided numerous possibilities for its exploitation bl both medical applications and 3D animation. In this paper, we present our interactive tools which enable extraction of surfaces for different organs, including bones, muscles, fascia, and skin, from the VHD. The reconstructed surfaces then are used for defining the inter-relationship of organs, a process bye refer to as topological modeling. A data base is constructed, which encapsulates structural, topological, mechanical and other relevant information about organs. A 3D interactive tool enables the building and editing of this data base. Such a data base can later be used for different applications in fields such as medicine, sports, education, and entertainment.

Abstract:   Augmented reality shows great promises in fields where a simulation in situ would be impossible or too expensive. When mixing synthetic and real objects in the same animated sequence, we must be sure that the geometrical coherence as well as the photometrical coherence is ensured. One major challenge is to compute the camera viewpoint with sufficient accuracy to ensure a satisfactory composition. We especially address this point in this paper using computer vision techniques and robust statistical methods. We prove that such techniques make it possible to compute almost automatically the viewpoint for long video sequences even for bad quality images in outdoor environments. Significant results on the lighting simulation of the bridges of Paris are shown.

Abstract:   Extraction of the shoreline in SAR images is a difficult task to perform using simple image processing operations such as grey-value thresholding, due to the presence of speckle and because the signal returned from the sea surface may be similar to that from the land. A semiautomatic method for detecting the shoreline accurately and efficiently in ERS-1 SAR images is presented. This is aimed primarily at a particular application; namely the construction of a digital elevation model of an intertidal zone using SAR images and hydrodynamic model output, but could be carried over to other applications. A coarse-fine resolution processing approach is employed, in which sea regions are first detected as regions of low edge density in a low resolution image, then image areas near the shoreline are subjected to more elaborate processing at high resolution using an active contour model. Over 90% of the shoreline detected by the automatic delineation process appear visually correct.

Abstract:   A key problem in the interpretation of visual form is the partitioning of a shape into components that correspond to the parts of an object. This paper presents a method for partitioning a set of surface estimates obtained with a laser range finding system into subsets corresponding to such parts. Parts are defined implicitly by means of a feature set that identifies putative part boundaries that have been computed by external means. The strategy employed makes use of two complementary representations for surfaces: one that describes local structures in terms of differential properties (e.g., edges, lines, contours) and the other that represents the surface as a collection of smooth patches at different scales. It is shown that by enforcing a consistent interpretation between these two representations, it is possible to derive a partitioning algorithm that is both efficient and robust. Examples of its performance on a set of range images are presented. (C) 1996 Academic Press, Inc.

Abstract:   Image and video compression is becoming an increasingly important area of investigation, with numerous applications to video conferencing, interactive education, home entertainment, and potential applications to earth observation, medical imaging, digital libraries, and many other areas. In this paper we describe a novel neural network technique for video compression, using a ''point-process'' type neural network model we have developed [1]-[4] which is closer to biophysical reality and is mathematically much more tractable than standard models. Our algorithm uses an adaptive approach based upon the users' desired video quality Q, and achieves compression ratios of up to 500:1 for moving gray-scale images, based on a combination of motion detection, compression ratio of over 1000:1 for full-color video sequences with the addition of the standard 4:1:1 spatial subsampling ratios in the chrominance images. The signal-to-noise ratio (SNR) obtained varies with the compression level and ranges from 29 dB to over 34 dB. Our method is computationally fast so that compression and decompression could possibly be preformed in real-time software. Compression is preformed using a combination of motion detection, neural networks, and temporal subsampling of frames. A set of neural networks is used to adaptively select the desired compression of each picture block as a function of the reconstruction quality. The motion detection process separates out regions of the frame which need to be retransmitted. Temporal subsampling of frames, along with reconstruction technique, lead to the high compression ratios reported in this paper.

Abstract:   In this paper, we discuss some uses of curve evolution theory for problems in computer vision. We concentrate on three problem areas: shape theory, active contours, and geometric invariant scale spaces. The solutions to these key problems will all be based on flows which are obtained in a completely natural manner from geometric and physical principles.

Abstract:   The theory of active contours models the problem of contour recovery as an energy minimization process. The computational solutions based on dynamic programming require that the energy associated with a contour candidate can be decomposed into an integral of local energy contributions. In this paper we propose a grammatical framework that can model different local energy models and a set of allowable transitions between these models. The grammatical encodings are utilized to represent a priori knowledge about the shape of the object and the associated signatures in the underlying images. The variability encountered in numerical experiments is addressed with the energy minimization procedure which is embedded in the grammatical framework. We propose an algorithmic solution that combines a nondeterministic version of the Knuth-Morris-Pratt algorithm for string matching with a time-delayed discrete dynamic programming algorithm for energy minimization. The numerical experiments address practical problems encountered in contour recovery such as noise robustness and occlusion.

Abstract:   This paper describes a new global shape parameterization for smoothly deformable three-dimensional (3-D) objects, such as those found in biomedical images, whose diversity and irregularity make them difficult to represent in terms of fixed features or parts. This representation is used for geometric surface matching to 3-D medical image data, such as from magnetic resonance imaging (MRI). The parameterization decomposes the surface into sinusoidal basis functions. Four types of surfaces are modeled: tori, open surfaces, closed surfaces and tubes. This parameterization allows a wide variety of smooth surfaces to be described with a small number of parameters. Extrinsic model-based information is incorporated by introducing prior probabilities on the parameters. Surface finding is formulated as an optimization problem, Results of the method applied to synthetic images and 3-D medical images of the heart and brain are presented.

Abstract:   Iterative deblurring methods using the expectation maximization (EM) formulation and the algebraic reconstruction technique (ART), respectively, are adapted for metal artifact reduction in medical computed tomography (CT). In experiments with synthetic noise-free and additive noisy projection data of dental phantoms, it is found that both simultaneous iterative algorithms produce superior image quality as compared to filtered backprojection after linearly fitting projection gaps. Furthermore, the EM-type algorithm converges faster than the ART-type algorithm in terms of either the I-divergence or Euclidean distance between ideal and reprojected data in our simulation. Also, for a given iteration number, the EM-type deblurring method produces better image clarity but stronger noise than the ART-type reconstruction. The computational complexity of EM- and ART-based iterative deblurring is essentially the same, dominated by reprojection and backprojection. Relevant practical and theoretical issues are discussed.

Abstract:   This article provides a tutorial introduction to visual servo control of robotic manipulators, Since the topic spans many disciplines our goal is limited to providing a basic conceptual framework, We begin by reviewing the prerequisite topics from robotics and computer vision, including a brief review of coordinate transformations, velocity representation, and a description of the geometric aspects of the image formation process, We then present a taxonomy of visual servo control systems, The two major classes of systems, position-based and image-based systems, are then discussed in detail, Since any visual servo system must be capable of tracking image features in a sequence of images, we also include an overview of feature-based and correlation-based methods for tracking, We conclude the tutorial with a number of observations on the current directions of the research field of visual servo control.

Abstract:   In this paper, we analyze geometric active contour models from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. This leads to a novel edge-detection paradigm in which the feature of interest may be considered to lie at the bottom of a potential well. Thus an edge-seeking curve is attracted very naturally and efficiently to the desired feature. Comparison with the Allen-Cahn model clarifies some of the choices made in these models, and suggests inhomogeneous models which may in return be useful in phase transitions. We also consider some 3-dimensional active surface models based on these ideas. The justification of this model rests on the careful study of the viscosity solutions of evolution equations derived from a level-set approach.

Abstract:   Active contour models have proven to be a promising approach for data driven object tracking without knowledge about the problem domain and the object. Problems arise in case of fast moving objects and in natural scenes with heterogeneous background. In these cases, a prediction step is an essential part of the tracking mechanism. In this paper we describe a new approach for modelling the contour of moving objects in the 3D world. The key point is the description of moving objects by a simplified geometric model, the sc-called bounding volume. The contour of moving objects is predicted by estimating the movement and the shape of the bounding volume in the 3D world and by projecting its contour to the image plane. Stochastic optimization algorithms are used to estimate shape parameters of the bounding volume. The 2D contour of the bounding volume is used to initialize the active contour, which then extracts the contour of the moving object. Thus, an update of the motion and model parameters of the bounding volume is possible. No task specific knowledge and no a priori knowledge about the object is necessary. We will show that in the case of convex polyhedral bounding volumes, this method can be applied to real-time closed-loop object tracking on standard Unix workstations. Furthermore, we present experiments which prove that the robustness for tracking moving objects in front of a heterogeneous background can be improved.

Abstract:   This paper presents a new approach for visual tracking and servoing in robotics. We introduce deformable active models as a powerful means for tracking a rigid or semi-rigid (possibly partially occluded) object in movement within the manipulator's workspace. Deformable models imitate, in real-time, the dynamic behavior of elastic structures. These computer-generated models are designed to capture the silhouette of objects with well-defined boundaries, in terms of image gradient. By means of an eye-in-hand robot arm configuration, the desired motion of the end-effector is computed with the objective of keeping the target's position and shape invariant with respect to the camera frame. Optimal estimation and control techniques (LQG regulator) have been successfully implemented in order to deal with noisy measurements provided by our vision sensor. Experimental results are presented for the tracking of a rigid or semi-rigid object. The experiments performed in a real-time environment show the effectiveness and robustness of the proposed method for servoing tasks based on visual feedback.

Abstract:   Unlike The time-consuming contour tracking method of snakes [5] which requires a considerable number of iterated computations before contours are successfully tracked down, we present a faster and accurate model-based ''landmarks'' tracking method where a single iteration of the dynamic programming is sufficient to obtain a local minimum to an integral measure of the elastic and the image energy functionals. The key lies in choosing a relatively small number of salient ''landmarks'', or features of objects, rather than their contours as a target of tracking within the image structure. The landmarks comprising singular points along the model contours are tracked down within the image structure all inside restricted search areas of 41 x 41 pixels whose respective locations in image structure are dictated by their locations in the model. A Manhattan distance and a template corner detection function of Singh and Shneier [7] are used as elastic energy and image energy respectively in the algorithm. A first approximation to the image contour is obtained in our method by applying the thin-plate spline transformation of Bookstein [2] using these landmarks as fixed points of the transformation which is capable of preserving a global shape information of the model including the relative configuration of landmarks and consequently surrounding contours of the model in the image structure. The actual image contours are further tracked down by applying an active edge tracker using now simplified line search segments so that individual differences persisting between the mapped model contour are substantially eliminated. We have applied our method tentatively to portraits of a class album to demonstrate the effectiveness of the method. Our experiments convincingly show that using only about 11 feature points our method provides not only a much improved computational complexity requiring only 0.94 sec. in CPU time by SGI's indigo2 but also more accurate shape representations than those obtained by the snakes methods. The method is powerful in a problem domain where the model-based approach is applicable, possibly allowing real time processing because a most time consuming algorithm of corner template evaluation can be easily implemented by parallel processing firmware.

Abstract:   Research in very low-bit rate coding has made significant advancements in the past few years. Most recently, the introduction of the MPEG-4 proposal has motivated a wide variety of approaches aimed al achieving a new level of video compression. In this paper we review progress in VLBV categorized into 3 main areas: (1) Waveform coding, (2) 2D Content-based coding, and (3) Model-based coding. Where appropriate we also described proposals to the MPEG-4 committee in each of these areas.

Abstract:   We describe a segmentation processor that is optimal for tracking the shape of a target with random white Gaussian intensity appearing on a random white Gaussian spatially disjoint background. This algorithm, based on an active contours model (snakes), consists of correlations of binary reference's with preprocessed versions of the scene image. This result can provide a practical method to adapt the reference image to correlation techniques. (C) 1996 Optical Society of America

Abstract:   Energy-minimizing active contour models or snakes can be used in many applications such as edge detection, motion tracking, image matching, computer vision, and three-dimensional (3-D) reconstruction. We present a novel snake that is superior both in accuracy and convergence speed over previous snake algorithms. High performance is achieved by using spline representation and dividing the energy-minimization process into multiple stages. The first stage is designed to optimize the convergence speed in order to allow the snake to quickly approach the minimum-energy state. The second stage is devoted to snake refinement and to local minimization of energy, thereby driving the snake to a quasiminimum-energy state. The third stage uses the Bellman optimality principle to fine-tune the snake to the global minimum-energy state. This three-stage scheme is optimized for both accuracy and speed.

Abstract:   We present a unified approach to noise removal, image enhancement, and shape recovery in images. The underlying approach relies on the level set formulation of curve and surface motion, which leads to a class of PDE-based algorithms. Beginning with an image, the first stage of this approach removes noise and enhances the image by evolving the image under flow controlled by min/max curvature and by the mean curvature. This stage is applicable to both salt-and-pepper grey-scale noise and full-image continuous noise present in black and white images, grey-scale images, texture images, and color images. The noise removal/enhancement schemes applied in this stage contain only one enhancement parameter, which in most cases is automatically chosen. The other key advantage of our approach is that a stopping criteria is automatically picked from the image; continued application of the scheme produces no further change. The second stage of our approach is the shape recovery of a desired object; we again exploit the level set approach to evolve an initial curve/surface toward the desired boundary, driven by an image-dependent speed function that automatically stops at the desired boundary.

Abstract:   The complexity and congestion of current transportation systems often produce traffic situations that jeopardize the safety of the people involved, These situations vary from maintaining a safe distance behind a leading vehicle to safely allowing a pedestrian to cross a busy street. Environmental sensing plays a critical role in virtually all of these situations, Of the sensors available, vision sensors protide information that Is richer and more complete than other sensors, making them a logical choice for a multisensor transportation system, In this paper we propose robust detection and tracking techniques for intelligent vehicle-highway applications where computer vision plays a crucial role, In particular, se demonstrate that the Controlled Active Vision framework [15] can be utilized to provide a visual tracking modality to a traffic advisory system in order to increase the overall safety margin in a variety bf common traffic situations, We have selected two application examples. vehicle tracking and pedestrian tracking, to demonstrate that the framework fan provide precisely the type of information required to effectively manage the given traffic situation.

Abstract:   We present a method for nonrigid motion analysis in time sequences of volume images (4D data). In this method, nonrigid motion of the deforming object contour is dynamically approximated by a physically-based deformable surface. In order to reduce the number of parameters describing the deformation, we make use of a modal analysis which provides a spatial smoothing of the surface. The deformation spectrum, which outlines the main excited modes, can be efficiently used for deformation comparison. Fourier analysis on time signals of the main deformation spectrum components provides a temporal smoothing of the data. Thus a complex nonrigid deformation is described by only a few parameters: the main excited modes and the main Fourier harmonics. Therefore, 4D data can be analyzed in a very concise manner. The power and robustness of the approach is illustrated by various results on medical data. We believe that our method has important applications in automatic diagnosis of heart diseases and in motion compression.

Abstract:   An efficient and robust approach, which is based on wavelet transform (WT), is proposed to contour extraction for medical ultrasonic images having low signal-to-noise ratio. Furthermore, the best wavelet features for profile analysis is estimated by GAs without manual operation. No image preprocessing is needed, so computation time is fast. Experimental results to confirm the proposed algorithm are also included.

Abstract:   This paper describes an automatic formant tracking algorithm incorporating speech knowledge. It operates in two phases. The first detects and interprets spectrogram peak lines in terms of formants. The second uses an image contour extraction method to regularise the peak lines thus detected. Speech knowledge served as acoustic constraints to guide the interpretation of peak lines. The proposed algorithm has the advantage of providing formant trajectories which, in addition to being sufficiently close to the spectral peaks of the respective formants, are sufficiently smooth to allow an accurate evaluation of formant transitions. The results obtained highlight the interest of the proposed approach.

Abstract:   In this paper, we present a weighted geometrical feature (WGF) registration algorithm. Its efficacy is demonstrated by combining points and a surface. The technique is an extension of Besl and McKay's iterative closest point (ICP) algorithm. We use the WGF algorithm to register X-ray computed tomography (CT) and T2-weighted magnetic resonance (MR) volume head images acquired from eleven patients that underwent craniotomies in a neurosurgical clinical trial. Each patient had five external markers attached to transcutaneous posts screwed into the outer table of the skull. We define registration error as the distance between positions of corresponding markers that are not used for registration. The CT and MR images are registered using fiducial points (marker positions) only, a surface only, and various weighted combinations of points and a surface. The CT surface is derived from contours corresponding to the inner surface of the skull. The MR surface is derived front contours corresponding to the cerebrospinal fluid (CSF)-dura interface. Registration using points and a surface is found to be significantly more accurate than registration using only points or a surface.

Abstract:   This paper examines the problem of obtaining a mathematical representation of the outer cortex of the human brain, which is a key problem in several applications, including morphological analysis of the brain, and spatial normalization and registration of brain images. A parameterization of the outer cortex is first obtained using a deformable surface algorithm which, motivated by the structure of the cortex, is constructed to find the central layer of thick surfaces. Based on this parameterization, a hierarchical representation of the outer cortical structure is proposed through its depth map and its curvature maps at various scales. Various experiments on magnetic resonance data are presented.

Abstract:   We propose a method for tracking the motion and intensity variations of a 2-D mildly deformable image object using a hierarchical 2-D mesh model. The proposed method is applied to synthetic object transfiguration, namely, replacing an object in a real video clip with another synthetic or natural object via digital postprocessing. Successful transfiguration requires accurate tracking of both motion and intensity (contrast and brightness) variations of the object-to-be-replaced so that the replacement object can be rendered in exactly the same way from a single still picture. The proposed method is capable of tracking image regions corresponding to scene objects with nonplanar and/or mildly deforming surfaces, accounting for intensity variations, and is shown to be effective with real image sequences. (C) 1996 Academic Press, Inc.

Abstract:   Compact set valued dynamical systems have a large field of applications in image processing and morphogenesis modelling. In section 2 of this paper, we will define the notion of compact set valued Row. In section 3, we will propose some examples of potential Rows used in 3D-image contouring. In section 4, we will introduce the notion of mixed potential-hamiltonian flows, which could be used in 4D-image contouring, which generalizes the 2D potential-hamiltonian contouring method. Finally, in section 5 we will give a simple example of compact set valued iterations, and in section 6 an example of distribution tube iterations.

Abstract:   This paper proposes a method to extract regions of a deformable object from several views of it while finding the correspondence of the object among the views. The method has been developed to analyze X-ray images of a stomach. Owing to the physical (not physiological) deformation oi the stomach and changes of the camera angle, the shape oi the stomach regions are fairly different among the Images. In order to collectively analyze these images, we use an elastic stomach model. Firstly, our method builds an elastic stomach model based on the stomach shape in one image. Considering each photographing condition, the deformation of the stomach in each image is simulated with the elastic model. Referring to the predicted contour which is obtained by projecting the deformed model from the camera angle of each image, the contour is robustly extracted from noisy images in a model-driven way. Since the predicted contour registered in each image corresponds with the elastic model, the position of each stomach part in the image is simultaneously obtained; corresponding parts can be found among the images through the model. Experimental results of analyzing several types of stomach X-ray images are shown and discussed.

Abstract:   This paper describes an image metamorphosis technique to handle scattered feature constraints specified with points, polylines, and splines. Solutions to the following three problems are presented: feature specification, warp generation, and transition control. We demonstrate the use of snakes to reduce the burden of feature specification. Next, we propose the use of multilevel free-form deformations (MFFD) to compute C-2-continuous and one-to-one mapping functions among the specified features. The resulting technique, based on B-spline approximation, is simpler and faster than previous warp generation methods. Furthermore, it produces smooth image transformations without undesirable ripples and foldovers. Finally, we simplify the MFFD algorithm to derive transition functions to control geometry and color blending. Implementation details are furnished and comparisons among Various metamorphosis techniques are presented.

Abstract:   A novel, robust algorithm for connectivity detection in the shape recognition process has been developed. The algorithm is a simplified version of the snake or active contour technique for object boundary detection. Access to a case base and constraint system is available at all stages of the process which increases the probability that semantically meaningful objects will be detected. The technique has proved valuable for a number of applications from the aerospace industry including shape recognition and fatigue crack detection. The algorithm has also been used to generate an improved version of the STIRS technique for shape recognition. Copyright (C) 1996 Elsevier Science Ltd

Abstract:   This paper proposes a segmentation method for a quantitative image diagnosis as a means of realizing an objective diagnosis of the frontal lobe atrophy, From the data obtained on the grade of membership, the fractal dimensions of the cerebral tissue [cerebral spinal fluid (CSF), gray matter, and white matter] and the contours are estimated, The mutual relationship between the degree of atrophy and the fractal dimension has been analyzed based on the estimated fractal dimensions, Using a sample of 42 male and Female cases, ranging in age from 50's to 70's, it has been concluded that the frontal lobe atrophy can be quantified by regarding it as an expansion of CSF region on the magnetic resonance imaging (MRI) of the brain, Furthermore, when the process of frontal lobe atrophy is separated into early and advanced stages, the volumetric change of CSF and white matter in frontal lobe displays meaningful differences between the two stages, demonstrating that the fractal dimension of CSF rises with the progress of atrophy, Moreover, an interpolation method for three-dimensional (3-D) shape reconstruction of the region of diagnostic interest is proposed and 3-D shape visualization, with respect to the degree and form of atrophy, is performed on the basis of the estimated fractal dimension of the segmented cerebral tissue.

Abstract:   This paper describes a robust fully automatic method for segmenting the brain from head MR images, which works even in the presence of RF inhomogeneities. It has been successful in segmenting the brain in every slice from head images acquired from three different MRI scanners, using different resolution images and different echo sequences. The three-stage integrated method employs image processing techniques based on anisotropic filters, ''snakes'' contouring techniques, and a-priori knowledge. First the background noise is removed leaving a head mask, then a rough outline of the brain is found, and finally the rough brain outline is refined to a final mask.

Abstract:   In this paper we present a method for the fully automatic segmentation of cell nuclei from 3D confocal laser microscopy images. The method is based on the combination of previously proposed techniques which have been refined for the requirements of this task. A 3D extension of a wave propagation technique applied to gradient magnitude images allows us a precise initialization of elastically deformable Fourier models and therefore a fully automatic image analysis. The shape parameters are transformed into invariant descriptors and provide the basis of a statistical analysis of cell nucleus shapes. This analysis will be carried out in order to determine average intersection lengths between cell nuclei and single particle tracks of ionizing radiation. This allows a quantification of absorbed energy on living cells leading to a better understanding of the biological significance of exposure to radiation in low doses.

Abstract:   A novel interactive segmentation method has been developed which uses estimated boundaries, generated from cores, to initialize a scale-space boundary evolution process in greyscale medical images. Presented is an important addition to core extraction methodology that improves core generation for objects that are in the presence of interfering objects. The boundary at the scale of the core (BASOC) and its associated width information, both derived from the core, are used to initialize the second stage of the segmentation process. In this automatic refinement stage, the BASOC is allowed to evolve in a spline-snake-like manner that makes use of object-relevant width information to make robust measurements of local edge positions.

Abstract:   To overcome limitations of the conventional 'toward-axis' voxel-removal way of thinning operations, a new 'along-axis' style of algorithm was developed for topological information acquisition of tree-like objects like vascular shapes based on region-growing technique. The theory of mathematical morphology is extended for closed space inside binary shapes, and the 'closed space dilation' operation is introduced as generalized form of region growing. Using synthetic and clinical 3D images, its superior features, such as parametric controllability were shown.

Abstract:   RATIONALE AND OBJECTIVES. AS contrast agents that selectively target normal lymph nodes are undergoing development and evaluation, it has become important to accurately and reproducibly determine nodal boundaries to study. the agents and determine such values as lymph node area or mean nodal contrast concentration. This study was performed to evaluate the accuracy of different two-dimensional computer segmentation methods, tested on acrylic phantoms constructed to imitate the appearance of lymph nodes surrounded bg fat. METHODS. Five segmentation techniques (manual tracing, semiautomatic local criteria threshold selection, Sobel/watershed technique, interactive deformable contour algorithm and thresholding) were evaluated using phantoms, Subsequently, the first three methods were applied to the images of enhanced lymph nodes in rabbits. RESULTS. Minimum errors in phantom area measurement (<5%) and interoperator variation (<5%) were seen with the Sobel/watershed technique and the interactive deformable contour algorithm, These two techniques were significantly better than thresholding and semiautomated thresholding based on local properties. CONCLUSION. Methods based on Sobel edge detection offer more objective tools than thresholding methods for segmenting objects similar to lymph nodes in computed tomography images, Both methods, Sobel/watershed and interactive deformable contour algorithm, are fast and have simple user interfaces.

Abstract:   An algorithm is presented for computing a decomposition of planar shapes into convex subparts represented by ellipses, The method is invariant to projective transformations of the shape, and thus the conic primitives can be used for matching and definition of invariants in the same way as points and lines. The method works for arbitrary planar shapes admitting at least four distinct tangents and it is based on finding ellipses with four points of contact to the given shape. The cross ratio computed from the four points on the ellipse can then be used as a projectively invariant index. It is demonstrated that a given shape has a unique parameter-free decomposition into a finite set of ellipses with unit cross ratio. For a given shape, each pair of ellipses can be used to compute two independent projective invariants. The set of invariants computed for each ellipse pair can be used as indexes to a hash table from which model hypothesis can be generated Examples of shape decomposition and recognition are given for synthetic shapes and shapes extracted from grey level images of real objects using edge detection.

Abstract:   Segmentation of(noisy) images containing a complex ensemble of objects is difficult to achieve on the basis of local image information only. It is advantageous to attack the problem of object boundary extraction by a model-based segmentation procedure, Segmentation is achieved by tuning the parameters of the geometrical model in such a way that the boundary template locates and describes the object in the image in an optimal way, The optimality of the solution is based on an objective function taking into account image information as well as the shape of the template. Objective functions in literature are mainly based on the gradient magnitude and a measure describing the smoothness of the template. In this contribution, we propose a new image objective function based on directional gradient information derived from Gaussian smoothed derivatives of the image data, The proposed method is designed to accurately locate an object boundary even in the case of a conflicting object positioned close to the object of interest, We further introduce a new smoothness objective to ensure the physical feasibility of the contour. The method is evaluated on artificial data, Results on real medical images show that the method is very effective in accurately locating object boundaries in very complex images. (C) 1996 Academic Press, Inc.

Abstract:   We report a system for PET-MRI registration that is improved or optimized in several areas: (1) Automatic scalp/brain segmentation replaces manual drawing operations, (2) a new fast and accurate method of image registration, (3) visual assessment of registration quality is enhanced by composite imaging methods (i.e., fusion) and (4) the entire procedure is embedded in a commercially available scientific visualization package, thereby providing a consistent graphical user interface. The segmentation algorithm was tested on 17 MRI data sets and was successful in all cases. Accuracy of image registration was equal to that of the Woods algorithm, but 10 times faster for PET-PET and 4 times faster for PET-MRI. The image fusion method allows detection of misalignments on the order of 2-3 mm. These results demonstrate an integrated system for intermodality image registration, which is important because the procedure can be performed by technicians with no anatomic knowledge and reduces the required time from hours to about 15 min on a modern computer workstation. (C) 1996 Academic Press, Inc.

Abstract:   A hybrid attenuation correction technique (ACT) is under development for F-18-FDG total body positron emission tomography (PET). With a short transmission scan of the thorax, any time within a few days of the imaging session, this technique can correct for attenuation in the entire body, Segmentation, registration, and active contour finding techniques are applied to both emission and short transmission images to locate and map the major attenuating structures in the body. This technique eliminates the need for the patient to remain still from the start of the transmission scan to the end of the emission scan without the added noise of simultaneous or post emission transmission scan measurements, The results of volunteer studies are comparable to standard measured ACT, both visually and quantitatively, The efficient use of scanner time and improved patient comfort make this technique particularly suitable for clinical imaging.

Abstract:   By using the wavelet transform, we develop a hierarchical planar curve descriptor that decomposes a curve into components of different scales so that the coarsest scale components carry the global approximation information while the finer scale components contain the local detailed information, We show that the wavelet descriptor has many desirable properties such as multiresolution representation, invariance, uniqueness, stability, and spatial localization, A deformable wavelet descriptor is also proposed by interpreting the wavelet coefficients as random variables, The applications of the wavelet descriptor to character recognition and model-based contour extraction from low SNR images are examined, Numerical experiments are performed to illustrate the performance of the wavelet descriptor.

Abstract:   Traditionally, Markov random field (MRF) models have been used in low-level image analysis. This correspondence presents an MRF-based scheme to perform object delineation. The proposed edge-based approach involves extracting straight lines from the edge map of an image. Then, an MRF model is used to group these lines to delineate buildings in aerial images.

Abstract:   Objective: A new technique for analyzing the morphology of the corpus callosum is presented, and it is applied to a group of elderly subjects. Materials and Methods: The proposed approach normalizes subject data into the Talairach space using an elastic deformation transformation. The properties of this transformation are used as a quantitative description of the callosal shape with respect to the Talairach atlas, which is treated as a standard. In particular, a deformation function measures the enlargement/shrinkage associated with this elastic deformation. Intersubject comparisons are made by comparing deformation functions. Results: This technique was applied to eight male and eight female subjects. Based on the average deformation functions of each group, the posterior region of the female corpus callosum was found to be larger than its corresponding region in the males. The average callosal shape of each group was also found, demonstrating visually the callosal shape differences between the two groups in this sample. Conclusion: The proposed methodology utilizes the full resolution of the data, rather than relying on global descriptions such as area measurements. The application of this methodology to an elderly group indicated sex-related differences in the callosal shape and size.

Abstract:   This paper presents a novel image analysis scheme for accurate detection of fruit blemishes. The detection procedure consists of two steps: initial segmentation and refinement. In the first step, blemishes are coarsely segmented out with a flooding algorithm and in the second step an active contour model, i.e. a snake algorithm, is applied to refine the segmentation so that the localization and size accuracy of detected blemishes is improved. The concept and the formulation of the snake algorithm are briefly introduced and then the refinement procedure is described. The initial tests for sample apple images have shown very promising results.

Abstract:   Effective surgical planning requires 3D images that show tumor location relative to key blood vessels. This research uses volume rendering of CT data to meet these requirements.

Abstract:   Grenander et al. (1991) proposed a conditional cyclic Gaussian Markov random field model for the edges of a closed outline in the plane. In this paper the model is recast as an improper cyclic Gaussian Markov random field for the vertices. The limiting behaviour of this model when the vertices become closely spaced is also described and in particular its relationship with the theory of 'snakes' (Kass et al. 1987) is established. Applications are given in Grenander et al. (1991), Mardia el al. (1991) and Kent et al. (1992).

Abstract:   Parametric deformable models have been extensively and very successfully used for reconstructing free-form curves and surfaces, and for tracking nonrigid deformations, but they require previous knowledge of the topological type of the data, and good initial curve or surface estimates. With deformable models, it is also computationally expensive to check for and to prevent self-intersections while tracking deformations. The Implicit Simplicial Models that we introduce in this paper are implicit curves and surfaces defined by piece-wise linear functions. This representation allows for local deformations, control of the topological type, and prevention of self-intersections during deformations. As a first application, we also describe in this paper an algorithm for two-dimensional curve reconstruction from unorganized sets of data points. The topology, the number of connected components, and the geometry of the data are all estimated using an adaptive space subdivision approach. The main four components of the algorithm are topology estimation, curve fitting, adaptive space subdivision, and mesh relaxation.

Abstract:   This paper proposes a segmentation algorithm using deformable template models to segment a vehicle of interest both from the stationary complex background and other moving vehicles in an image sequence. We define a polygonal template to characterize a general model of a vehicle and derive a prior probability density function to constrain the template to be deformed within a set of allowed shapes. We propose a likelihood probability density function which combines motion information and edge directionality to ensure that the deformable template is contained within the moving areas in the image and its boundary coincides with strong edges with the same orientation in the image. The segmentation problem is reduced to a minimization problem and solved by the Metropolis algorithm. The system was successfully tested on 405 image sequences containing multiple moving vehicles on a highway.

Abstract:   We propose a general object localization and retrieval scheme based on object shape using deformable templates. Prior knowledge of an object shape is described by a prototype template which consists of the representative contour/edges, and a set of probabilistic deformation transformations on the template. A Bayesian scheme, which is based on this prior knowledge and the edge information in the input image, is employed to find a match between the deformed template and objects in the image. Computational efficiency is achieved via a coarse-to-fine implementation of the matching algorithm. Our method has been applied to retrieve objects with a variety of shapes from images with complex background. The proposed scheme is invariant to location, rotation, and moderate scale changes of the template.

Abstract:   A Markov Random Field is used as a structural model of a deformable rectangular lattice. When used as a template prior in a Bayesian framework this model is powerful for making inferences about lattice structures in images, The model assigns maximum probability to the perfect regular lattice by penalizing deviations in alignment and lattice node distance, The Markov random field represents prior knowledge about the lattice structure, and through an observation model that incorporates the visual appearance of the nodes, we can simulate realizations from the posterior distribution. A maximum a posteriori (MAP) estimate, found by simulated annealing, is used as the reconstructed lattice. The model was developed as a central part of an algorithm for automatic analysis of genetic experiments, positioned in a lattice structure by a robot. The algorithm has been successfully applied to many images, and it seems to be a fast, accurate, and robust solution to the problem. Several possible extensions of the model are described. (C) 1996 Academic Press, Inc.

Abstract:   This paper presents an original approach to the problem of camera calibration using a calibration pattern, It consists of directly searching for the camera parameters that best project three-dimensional points of a calibration pattern onto intensity edges in an image of this pattern, without explicitly extracting the edges. Based on a characterization of image edges as maxima of the intensity gradient or zero-crossings of the Laplacian, we express the whole calibration process as a one-stage optimization problem. A classical iterative optimization technique is used in order to solve it. Our approach is different from the classical calibration techniques which involve two consecutive stages: extraction of image features and computation of the camera parameters. Thus, our approach is easier to implement and to use, less dependent on the type of calibration pattern that is used, and more robust. First, we describe the details of the approach, Then, we show some experiments in which two implementations of our approach and two classical two-stage approaches are compared, Tests on real and synthetic data allow us to characterize our approach in terms of convergence, sensitivity to the initial conditions, reliability, and accuracy. (C) 1996 Academic Press, Inc.

Abstract:   This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Different feature extraction methods are designed for different representations df the characters, such as solid binary characters, character contours, skeletons (thinned characters) or gray-level subimages of each individual character. The feature extraction methods are discussed in terms of invariance properties, reconstructability and expected distortions and variability of the characters. The problem of choosing the appropriate feature extraction method for a given application is also discussed. When a few promising feature extraction methods have been identified, they need to be evaluated experimentally to find the best method for the given application.

Abstract:   Facial feature extraction is an important step in automated visual interpretation and human face recognition. Among the facial features, the eye plays the most important part in the recognition process. The deformable template can be used in extracting the eye boundaries. However, the weaknesses of the deformable template are that the processing time is lengthy and that its success relies on the initial position of the template. in this paper, the head boundary is first located in a head-and-shoulders image. The approximate positions of the eyes are estimated by means of average anthropometric measures. Corners, the salient features of the eyes, are detected and used to set the initial parameters of the eye templates. The corner detection scheme introduced in this paper can provide accurate information about the corners. Based on the corner positions, we can accurately locate the templates in relation to the eye images and greatly reduce the processing time for the templates. The performance of the deformable template is assessed with and without using the information on corner positions. Experiments show that a saving in execution time of about 40% on average and a better eye boundary representation can be achieved by using the corner information.

Abstract:   MRI studies of first-pass contrast enhancement with polylysine-Gd-DTPA and myocardial tagging using spatial modulation of magnetization (SPAMM) were performed to assess the feasibility of a combined regional myocardial blood flow and 2D deformation exam, Instrumented closed-chest dogs were imaged at a baseline control state (Cntl) followed by two interventions: moderate coronary stenosis (St) achieved by partial occlusion of the left anterior descending (LAD) and moderate coronary stenosis with dobutamine loading (StD), Hypoperfusion of the anterior region (ANT) of the myocardium (LAD distribution) relative to the posterior wall (POS) based on the upslope of the signal intensity time curve from the contrast-enhanced MR images was demonstrated only with dobutamine loading (ANT:POS Cntl = 1.077 +/- 0.15 versus ANT:POS StD = 0.477 +/- 0.11, P < 0.03) and was confirmed with radiolabeled microspheres measurements (ANT:POS Cntl = 1.18 +/- 0.2 ml/min/g versus ANT:POS StD = 0.44 +/- 0.1 ml/min/g; P < 0.002). Significant changes in regional myocardial shortening were only seen in the StD state (P < 0.02); the anterior region showed impaired myocardial shortening with dobutamine loading (P = NS), whereas the nonaffected POS region showed a marked increase in shortening when compared with Cntl (Cntl = 0.964 +/- 0.02 versus StD = 0.884 +/- 0.03; P < 0.001). These results demonstrate that an integrated quantitative assessment of regional myocardial function and semiquantitative assessment of myocardial blood flow can be performed noninvasively with ultrafast MRI.

Abstract:   An appropriate space of one-pixel-wide closed (OPWC) boundary configurations is explicitly defined and an automatic algorithm to obtain OPWC contour estimates from a segmented image is presented. The motivation is to obtain a reasonable starting estimate for a Markov chain Monte Carlo-based (McMC-based) boundary optimization algorithm.

Abstract:   An enhanced snakes algorithm (ESA) for detecting object contours is designed and developed. In the ESA, a novel split and merge technique is added to the original snakes model to enhance the model to support the detection of concave object contours. A set of handtools is selected to evaluate the proposed algorithm, and the results are encouraging.

Abstract:   Tracing of left-ventricular epicardial and endocardial borders on echocardiographic sequences is essential for quantification of cardiac function. We designed a method based on an extension of active contour models to detect both epicardial and endocardial borders on short-axis cardiac sequences spanning the entire cardiac cycle, We validated the results by comparing the computer-generated boundaries to the boundaries manually outlined by four expert observers on 44 clinical data sets, The mean boundary distance between the computer-generated boundaries and the manually outlined boundaries was 2.80 mm (sigma = 1.28 mm) for the epicardium and 3.61 (sigma = 1.68 mm) for the endocardium, These distances were comparable to interobserver distances, which had a mean of 3.79 mm (sigma = 1.53 mm) for epicardial borders and 2.67 mm (sigma = 0.88 mm) for endocardial borders, The correlation coefficient between the areas enclosed by the computer-generated boundaries and the average manually outlined boundaries was 0.95 for epicardium and 0.91 for endocardium, The algorithm is fairly insensitive to the choice of the initial curve, Thus, we have developed an effective and robust algorithm to extract left-ventricular boundaries from echocardiographic sequences.

Abstract:   Active contour models, or ''snakes,'' developed in (Kass et al. 1988), use a simple physical model to track edges in image sequences. Snakes as originally defined however, tend to shrink, stretch and slide back and forth in unwanted ways along a tracked edge and are also confused by multiple edges, always grabbing the nearest one. In this paper a semi-automatic system is presented that combines motion estimation techniques with snakes to overcome these problems. An algorithm is presented that uses a block matching technique to guide the endpoints of the snake, optical flow to push the snake in the direction of the underlying motion, followed by the traditional snake edge-fitting minimization process. We use this technique for tracking facial features of an actor for driving computer animated characters.

Abstract:   A robust and adaptable model-based scheme for cell image interpretation is presented that can accommodate the wide natural variation in the appearance of cells. This is achieved using multiple models and an interpretation process that permits a smooth transition between models. Boundaries are represented using trainable statistical models that are invariant to transformations of scaling, shift, rotation and contrast; a Gaussian and a circular autoregressive (CAR) model are investigated. The interpretation process optimises the match between models and data using a Bayesian distance measure. We demonstrate how objects that vary in both shape and grey-level pattern can reliably be segmented. The results presented show that overall performance is comparable with that for manual segmentation; the area within the automatically and manually selected cell boundaries that is not common to both is less than 5% in 96% of the cases tested. The results also show that the computationally simpler Gaussian boundary model is at least as effective as the CAR model.

Abstract:   This paper addresses the implementation of image processing and computer vision techniques to automate tracer flow extraction in images obtained by the photochromic dye technique. This task is important in modeled arterial blood flow studies. Currently, it is performed via manual application of B-spline curve fitting. However, this is a tedious and error-prone procedure and its results are nonreproducible, In the proposed approach, active contours, snakes, are employed in a new curve-fitting method for tracer flow extraction in photochromic images. An algorithm implementing snakes is introduced to automate extraction, Utilizing correlation matching, the algorithm quickly locates and localizes all flow traces in the images. The feasibility of the method for tracer flow extraction is demonstrated. Moreover, results regarding the automation algorithm are presented showing its accuracy and effectiveness. The proposed approach for tracer flow extraction has potential for real-system application.

Abstract:   This paper addresses the problem of 3D surface reconstruction using image sequences. It has been shown that shape recovery from three or more occluding contours of the surface is possible given a known camera motion. Several algorithms, which have been recently proposed, allow such a reconstruction under the assumption of a linear camera motion. A new approach is presented which deals with the reconstruction problem directly from a discrete point of view. First, a theoretical study of the epipolar correspondence between occluding contours is achieved. A correct depth formulation is then derived from a local approximation of the surface up to order two. This allows the local shape to be estimated, given three consecutive contours, without any constraints on the camera motion. Experimental results are presented for both synthetic and real data.

Abstract:   The problem of image registration subsumes a number of problems and techniques in multiframe image analysis, including the computation of optic flow (general pixel-based motion), stereo correspondence, structure from motion, and feature tracking. We present a new registration algorithm based on spline representations of the displacement field which can be specialized to solve all of the above mentioned problems. In particular, we show how to compute local flow, global (parametric) flow, rigid flow resulting from camera egomotion, and multiframe versions of the above problems. Using a spline-based description of the flow removes the need for overlapping correlation windows, and produces an explicit measure of the correlation between adjacent flow estimates. We demonstrate our algorithm on multiframe image registration and the recovery of 3D projective scene geometry. mie also provide results on a number of standard motion sequences.

Abstract:   Several problems in early vision have been formulated in the past in a regularization framework. These problems, when discretized, lead to large sparse linear systems. In this paper, we present a novel physically based adaptive preconditioning technique which can be used in conjunction with a conjugate gradient algorithm to dramatically improve the speed of convergence for solving the aforementioned linear systems. A preconditioner, based on the membrane spline, or the thin plate spline, or a convex combination of the two, is termed a physically based preconditioner for obvious reasons. The adaptation of the preconditioner to an early vision problem is achieved via the explicit use of the spectral characteristics of the regularization filter in conjunction with the data. This spectral function is used to modulate the frequency characteristics of a chosen wavelet basis, and these modulated values are then used in the construction of our preconditioner. We present the preconditioner construction for three different early vision problems namely, the surface reconstruction, the shape from shading, and the optical flow computation problems. Performance of the preconditioning scheme is demonstrated via experiments on synthetic and real data sets. We note that our preconditioner outperforms other methods of preconditioning for these early vision problems, described in computer Vision literature.

Abstract:   Robot manipulators require knowledge about their environment in order to perform their desired actions. In several robotic tasks, vision sensors play a critical role by providing the necessary quantity and quality of information regarding the robot's environment. For example, ''visual servoing'' algorithms may control a robot manipulator in order to track moving objects that are being imaged by a camera. Current visual servoing systems often lack the ability to detect automatically objects that appear within the camera's field of view. In this research, we present a robust ''figure/ground'' framework for visually detecting objects of interest. An important contribution of this research is a collection of optimization schemes that allow tbe detection framework to operate within the real-time Limits of visual servoing systems. The most significant of these schemes involves the use of ''spontaneous'' and ''continuous'' domains. The number and location of continuous domains are,allowed to change over time, adjusting to the dynamic conditions of the detection process. We have developed actual servoing systems in order to test the framework's feasibility and to demonstrate its usefulness for visually controlling a robot manipulator. (C) 1997 Elsevier Science Ltd.

Abstract:   Flexible polyurethane foam is based on a 3-dimensional cellular network. The mechanical properties of foam material depend upon cell structure and cell size distribution. In this work, we use laser confocal microscopy to image the foam cells and recover its 3-dimensional cellular network. Based on this technique we provide a statistical analysis and compare several foam samples. Confocal microscopic images are also used to visualize foam compression. Images for foam network structure under different mechanical compressions are also obtained. Limitations of confocal microscope are discussed and a new method - nuclear magnetic resonance imaging is proposed.

Abstract:   In this paper, we describe how Active Shape Models (ASMs) have been used to accurately and robustly locate vertebrae in lateral Dual Energy X-ray Absorptiometry (DXA) images of the spine. DXA images are of low spatial resolution, and contain significant random and structural noise, providing a difficult challenge for object location methods. All vertebrae in the image were searched for simultaneously, improving robustness in location of individual vertebrae by making use of constraints on shape provided by the position of other vertebrae. We show that the use of ASMs with minimal user interaction allows accuracy to be obtained which is as good as that achievable by human operators, as well as high precision. Having located each vertebra, it is desirable to evaluate whether it has been located sufficiently accurately for shape measurements to be useful. We determined this on the basis of grey-level model fit, which was shown to usefully detect poorly located vertebrae, which should enable accuracy to be improved by rejecting proposed search solutions whose grey-level fit was poorer than a threshold. (C) 1997 Elsevier Science B.V.

Abstract:   We have developed a tool to automatically detect inner and outer skull boundaries of a fetal head in ultrasound images, These boundaries are used to measure biparietal diameter (BPD) and head circumference (HC). The algorithm is based on active contour models and takes 32 s on a Sun SparcStation 20/71, A high-performance desktop multimedia system called MediaStation 5000 (MS5000) is used as a model for our future ultrasound subsystem, On the MS5000, the optimized implementation of this algorithm takes 248 ms, The difference (between the computer-measured values on MS5000 and the gold standard) for BPD and HC was 1.43% (sigma = 1,00%) and 1.96% (sigma = 1.96%), respectively. According to our data analysis, no significant differences exist in the BPD and HC measurements made on the MS5000 and those measurements made on the Sun SparcStation 20/71, Reduction in the overall execution time from 32 s to 248 ms will help making this algorithm a practical ultrasound tool for sonographers, (C) 1997 World Federation for Ultrasound in Medicine and Biology.

Abstract:   We have designed and implemented a lipreading system that recognizes isolated words using only color video of human lips (without acoustic data). The system performs video recognition using ''snakes'' to extract visual features of geometric space, Karhunen-Loeve transform (KLT) to extract principal components in the color eigenspace, and hidden Markov models (HMM's) to recognize the combined visual features sequences. With the visual information alone, we were able to achieve 94% accuracy for ten isolated words.

Abstract:   We present an unsupervised technique for visual learning, which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for unimodal distributions) and a Mixture-of-Gaussians model (for multimodal distributions). These probability densities are then used to formulate a maximum-likelihood estimation framework for visual search and target detection for automatic object recognition and coding. Our learning technique is applied to the probabilistic visual modeling, detection, recognition, and coding of human faces and nonrigid objects, such as hands.

Abstract:   This paper deals with semi-automatic linear feature extraction from digital images for GIS data capture, where the identification task is performed manually on a single image, while a special automatic digital module performs the high precision feature tracking in two-dimensional (2-D) image space or even three-dimensional (3-D) object space. A human operator identifies the object from an on-screen display of a digital image, selects the particular class this object belongs to, and provides a very few coarsely distributed seed points. Subsequently, with these seed points as an approximation of the position and shape, the linear feature will be extracted automatically by either a dynamic programming approach or by LSB-Snakes (Least-Squares B-spline Snakes). With dynamic programming, the optimization problem is set up as a discrete multistage decision process and is solved by a time delayed'' algorithm. It ensures global optimality, is numerically stable, and allows for hard constraints to be enforced on the solution. In the least-squares approach, we combine three types of observation equations, one radiometric, formulating the matching of a generic object model with image data, and two that express the internal geometric constraints of a curve and the location of operator-given seed points. The solution is obtained by solving a pair of independent normal equations to estimate the parameters of the spline curve. Both techniques can be used in a monoplotting mode, which combines one image with its underlying DTM. The LSB-Snakes approach is also implemented in a multi-image mode, which uses multiple images simultaneously and provides for a robust and mathematically sound full 3D approach. These techniques are not restricted to aerial images. They can be applied to satellite and close-range images as well. The issues related to the mathematical modeling of the proposed methods are discussed and experimental results are shown in this paper too.

Abstract:   This contribution addresses the problem of pose estimation and tracking of vehicles in image sequences from traffic scenes recorded by a stationary camera. In a new algorithm, the vehicle pose is estimated by directly matching polyhedral vehicle models to image gradients without an edge segment extraction process. The new approach is significantly more robust than approaches that rely on feature extraction since the new approach exploits more information from the image data. We successfully tracked vehicles that were partially occluded by textured objects, e.g., foliage, where a previous approach based on edge segment extraction failed. Moreover, the new pose estimation approach is also used to determine the orientation and position of the road relative to the camera by matching an intersection model directly to image gradients. Results from various experiments with real world traffic scenes are presented.

Abstract:   A semiautomated feature extraction algorithm is presented for the extraction and measurement of the hippocampus from volumetric magnetic resonance imaging (MRI) head scans. This algorithm makes use of elements of both deformable model and region growing techniques and allows incorporation of a priori operator knowledge of hippocampal location and shape, Experimental results indicate that the algorithm is able to estimate hippocampal volume and asymmetry with an accuracy which approaches that of laborious manual outlining techniques.

Abstract:   BACKGROUND. Both axillary lymph node involvement and tumor anaplasia, as expressed by visually assessed grade, have been shown to be prognostically important in breast carcinoma outcome. In this study, axillary lymph node involvement was used as the standard against which prognostic estimations based on computer-derived nuclear features were gauged, METHODS, The prognostic significance of nuclear morphometric features determined by computer-based image analysis were analyzed in 198 consecutive preop preoperative samples obtained by fine-needle aspiration (FNA) from patients with invasive breast carcinoma. A novel multivariate prediction method was used to model the time of distant recurrence as a function of the nuclear features. Prognostic predictions based on the nuclear feature data were cross-validated to avoid overly optimistic conclusions. The estimated accuracy of these prognostic determinations was compared with determinations based on the extent of axillary lymph node involvement. RESULTS. The predicted outcomes based on nuclear features were divided into three groups representing best, intermediate, and worst prognosis, and compared with the traditional TNM lymph node stratification. Nuclear feature stratification better separated the prognostically best from the intermediate group whereas lymph node stratification better separated the prognostically intermediate from the worst group. Prognostic accuracy was not increased by adding lymph node status or tumor size to the nuclear features. CONCLUSIONS. Computer analysis of a preoperative FNA more accurately identified prognostically favorable patients than did pathologic examination of axillary lymph nodes and may obviate the need for routine axillary lymph node dissection. (C) 1997 American Cancer Society.

Abstract:   Variational methods for image segmentation try to recover a piecewise smooth function together with a discontinuity set which represents the boundaries of the segmentation. This paper deals with a variational method that constrains the formation of discontinuities along smooth contours. The functional to be minimized, which involves the computation of the geometrical properties of the boundaries, is approximated by a sequence of functionals which can be discretized in a straightforward way. Computer examples of real images are presented to illustrate the feasibility of the method. (C) 1997 Elsevier Science B.V.

Abstract:   Many strategies in computer vision assume the existence of general purpose models that can be used to characterize a scene or environment at various levels of abstraction. The usual assumptions are that a selected model is competent to describe a particular attribute and that the parameters of this model can be estimated by interpreting the input data in an appropriate manner (e.g., location of lines and edges, segmentation into parts or regions, etc.). This paper considers the problem of how to determine when those assumptions break down. The traditional approach is to use statistical misfit measures based on an assumed sensor noise model. The problem is that correct operation often depends critically on the correctness of the noise model. Instead, we show how this can be accomplished with a minimum of a priori knowledge and within the framework of an active approach which builds a description of environment structure and noise over several viewpoints.

Abstract:   The ultimate goal of machine vision is image understanding-the ability not only to recover image structure but also to know what it represents. By definition, this involves the use of models which describe and label the expected structure of the world. Over the past decade, model-based vision has been applied successfully to images of man-made objects. It has proved much more difficult to develop model-based approaches to the interpretation of images of complex and variable structures such as faces or the internal organs of the human body (as visualized in medical images). In such cases it has been problematic even to recover image structure reliably without a model to organize the often noisy and incomplete image evidence. The key problem is that of variability. To be useful, a model needs to be specific-that is, to be capable of representing only 'legal' examples of the modelled object(s). It has proved difficult to achieve this whilst allowing for natural variability. Recent developments have overcome this problem; it has been shown that specific patterns of variability in shape and grey-level appearance can be captured by statistical models that can be used directly in image interpretation. The details of the approach are outlined and practical examples from medical image interpretation and face recognition are used to illustrate how previously intractable problems can now be tackled successfully. It is also interesting to ask whether these results provide any possible insights into natural vision; for example, we show that the apparent changes in shape which result from viewing three-dimensional objects from different viewpoints can be modelled quite well in two dimensions; this may lend some support to the 'characteristic views' model of natural vision.

Abstract:   A new boundary detection approach for shape modeling is presented. It detects the global minimum of an active contour model's energy between two end points. Initialization is made easier and the curve is not trapped at a local minimum by spurious edges. We modify the ''snake'' energy by including the internal regularization term in the external potential term. Our method is based on finding a path of minimal length in a Riemannian metric. We then make use of a new efficient numerical method to find this shortest path. It is shown that the proposed energy, though based only on a potential integrated along the curve, imposes a regularization effect like snakes. We explore the relation between the maximum curvature along the resulting contour and the potential generated from the image. The method is capable to close contours, given only one point on the objects' boundary by using a topology-based saddle search routine. We show examples of our method applied to real aerial and medical images.

Abstract:   Deformable contour models are useful tools for image segmentation. However, many models depend mainly on local edge-based image features to guide the convergence of the contour. This makes the models sensitive to noise and the initial estimate. Our model incorporates region-based image features to improve its convergence and to reduce its dependence on initial estimation. Computational efficiency is achieved by an optimization strategy, modified from the greedy algorithm of Williams and Shah. The model allows a simultaneous optimization of multiple contours, making it useful for a large variety of segmentation problems.

Abstract:   An interpolation method using contours of organs as the control parameters is proposed to recover the intensity information in the physical gaps of serial cross-sectional images. In our method, contour models are used to generate the control lines required for the warping algorithm. Contour information derived from this contour model-based segmentation process is processed and used as the control parameters to warp the corresponding regions in both input images into compatible shapes. In this way, the reliability of establishing the correspondence among different segments of the same organs is improved and the intensity information for the interpolated intermediate slices can be derived more faithfully, To improve the efficiency for calculating the image warp in the field morphing process, a hierarchic decomposition process is proposed to localize the influence of each control line segment, In comparison with the existing intensity interpolation algorithms that only search for corresponding points in a small physical neighborhood, this method provides more meaningful correspondence relationships by warping regions in images into similar shapes before resampling to account for significant shape differences. Several sets of experimental result are presented to show that this method generates more realistic and less blurred interpolated images, especially when the shape difference of corresponding contours is significant. (C) 1997 John Wiley & Sons, Inc.

Abstract:   We present an active object recognition strategy which combines the use of an attention mechanism for focusing the search for a 3D object in a 2D image, with a viewpoint control strategy for disambiguating recovered object features. The attention mechanism consists of a probabilistic search through a hierarchy of predicted feature observations, taking objects into a set of regions classified according to the shapes of their bounding contours. We motivate the use of image regions as a focus-feature and compare their uncertainty in inferring objects with the uncertainty of more commonly used features such as lines or corners. If the features recovered during the attention phase do not provide a unique mapping to the 3D object being searched, the probabilistic feature hierarchy can be used to guide the camera to a new viewpoint from where the object can be disambiguated. The power of the underlying representation is its ability to unify these object recognition behaviors within a single framework. We present the approach in detail and evaluate its performance in the context of a project providing robotic aids for the disabled. (C) 1997 Academic Press.

Abstract:   Stent graft combination devices have been developed as a new alternative for treating abdominal aortic aneurysms. The major risk using this new technique with standard devices is the perigraft leak. In order to choose a suitable graft for each patient, and thus avoid such a risk, we have developed a program which provides three-dimensional representations of such aneurysms. Images of abdominal regions are obtained by spiral C.T.. These images are then transferred to a graphics workstation and processed to provide sets of contours which represent the shape of the aorta and other vessels. Then, a surface joining all these contours is computed; we obtain a tree-like structure represented as a set of generalized cylinders which are joined by means of flee-form surfaces. Such geometrical models provide an efficient mathematical support for further developments involving diagnosis, surgery and endoprostheses design.

Abstract:   For many medical applications including computer-assisted surgery, it is necessary to perform scientific computations, such as mechanical deformation, on anatomical structure models. Such patient-based anatomical models are often extracted from volumetric medical images as isosurfaces. In this paper, we introduce a new algorithm for the decimation of isosurfaces based on deformable models. The method emphasizes the creation of mesh of high geometric and topological properties well suited for performing scientific computation. rt allows a close control of the distance of the mesh to the isosurface as well a the overall smoothness of the mesh. The isosurface is stored in a data-structure that enables the fast computation of the distance to the isosurface. Finally, our method can handle very large datasets by merging pieces of isosurfaces.

Abstract:   We have developed an algorithm for segmenting objects with simple closed curves, such as the heart and the lungs, that is independent of the imaging modality used (e.g., MRI, CT, echocardiography). Our method is automatic and requires as initialization a single pixel within the boundaries of the object. Existing segmentation techniques either require much more information during initialization, such as an approximation to the object's boundary, or are not robust to the types of noisy data encountered in the medical domain. By integrating region-based and physics-based modeling techniques we have devised a hybrid design that overcomes these limitations. In our experiments we demonstrate that this integration automates and significantly improves the object boundary detection results, independent of the imaging modality used.

Abstract:   Efficient and powerful topologically adaptable deformable surfaces can be created by embedding and defining discrete deformable surface models in terms of an Affine Cell Decomposition (ACD) framework. The ACD framework, combined with a novel and original reparameterization algorithm, creates a simple but elegant mechanism for multiresolution deformable curve, surface, and solid models to ''flow'' or ''grow'' into objects with complex geometries and topologies, and adapt their shape to recover the object boundaries. ACD-based models maintain the traditional parametric physics-based formulation of deformable models, allowing them to incorporate a priori knowledge in the form of energy and force-based constraints, and provide intuitive interactive capabilities. This paper describes ACD-based deformable surfaces and demonstrates their potential for extracting and reconstructing some of the most complex biological structures from medical image volumes.

Abstract:   In this paper we address the problem of extracting geometric models from lour contrast volumetric images, given a template or reference shape of that model. We proceed by deforming a reference model in a volumetric image. This reference deformable model is represented as a simplex mesh submitted to regularizing shape constraint. Furthermore, we introduce an original approach that combines the deformable model framework with the elastic registration (based on iterative closest point algorithm) method. This new method increases the robustness of segmentation while allowing very complex deformation, of the original template. Examples of segmentation of the liver and brain ventricles are provided.

Abstract:   We present a couple of new algorithmic procedures for the detection of ridges in the modulus of the (continuous) wavelet transform of one-dimensional (1-D) signals, These detection procedures are shown to be robust to additive white noise, We also derive and test a new reconstruction procedure, The latter uses only information from the restriction of the wavelet transform to a sample of points from the ridge. This provides a very efficient way to code the information contained in the signal.

Abstract:   A novel geometric approach for three dimensional object segmentation is presented. The scheme is based on geometric deformable surfaces moving towards the objects to be detected, We show that this model is related to the computation of surfaces of minimal area (local minimal surfaces). The space where these surfaces are computed is induced from the three dimensional image in which the objects are to be detected. The general approach also shows the relation between classical deformable surfaces obtained via energy minimization and geometric ones derived from curvature flows in the surface evolution framework. The scheme is stable, robust, and automatically handles changes in the surface topology during the deformation. Results related to existence, uniqueness, stability, and correctness of the solution to this geometric deformable model are presented as well. Based on an efficient numerical algorithm for surface evolution, we present a number of examples of object detection in real and synthetic images.

Abstract:   The motion sensitivity of cardiac magnetic resonance imaging (MRI) can be exploited to measure the motion patterns within the heart wall and thus to noninvasively calculate the intramyocardial strain. The resulting large data sets pose a challenge for visualization, but offer the potential of a greatly improved picture of cardiac dynamics. This may have both basic research and clinical applications.

Abstract:   This paper describes an image segmentation technique in which an arbitrarily shaped contour was deformed stochastically until it fitted around an object of interest. The evolution of the contour was controlled by a simulated annealing process which caused the contour to settle into the global minimum of an image-derived ''energy'' function. The nonparametric energy function was derived from the statistical properties of previously segmented images, thereby incorporating prior experience. Since the method was based on a state space search for the contour with the best global properties, it was stable in the presence of image errors which confound segmentation techniques based on local criteria, such as connectivity. Unlike ''snakes'' and other active contour approaches, the new method could handle arbitrarily irregular contours in which each interpixel crack represented an independent degree of freedom. Furthermore, since the contour evolved toward the global minimum of the energy, the method was more suitable for fully automatic applications than the snake algorithm, which frequently has to be reinitialized when the contour becomes trapped in local energy minima. High computational complexity was avoided by efficiently introducing a random local perturbation in a time independent of contour length, providing control over the size of the perturbation, and assuring that resulting shape changes were unbiased. The method was illustrated by using it to find the brain surface in magnetic resonance head images and to track blood vessels in angiograms.

Abstract:   We present a novel method of velocity field estimation for the points on moving contours in a 2-D image sequence. The method determines the corresponding point in a next image frame by minimizing the curvature change of a given contour point. As a first step, snakes are used to locate smooth curves in 2-D imagery. Thereafter, the extracted curves are tracked continuously computing the corresponding point for each contour point. (C) 1997 Published by Elsevier Science B.V.

Abstract:   Development of an automated contour tracking method provides detection and tracking of the endocardial boundary using the energy minimization method without tracing a region of interest. The purpose of this study was to compare the automated contour tracking method and manually drawn methods for the measurement of left ventricular cavity areas and fractional area change. Apical four-chamber view was visualized and recorded for off-line analysis in 11 patients by means of two-dimensional echocardiography. The automated contour tracking method automatically traces the endocardial border from the recorded images and calculates left ventricular cavity areas (end-diastole and end-systole) and fractional area change. In the same images selected as end-diastole and end-systole in the automated contour tracking method, left ventricular endocardial border was manually traced to calculate left ventricular cavity areas and fractional area change. Both methods were compared by Linear regression analysis for the measurement of cavity areas and fractional area change. Left ventricular areas measured by the automated contour tracking method showed an excellent correlation with those by the manual method (end-diastole: r = 0.99, y = 0.83x + 2.6, standard error of the estimate = 1.5 cm(2); end-systole: r = 0.99, y = 0.96x - 0.8, standard error of the estimate = 1.2 cm(2)). The mean differences between the automated contour tracking and manual methods were -3.1 +/- 5.1 cm(2) and -1.6 +/- 2.4 cm(2) at end-diastole and end-systole, respectively. Fractional area change determined by the automated contour tracking method correlated well with that by the manual method (r = 0.95, y = 1.17x - 6.5, standard error of the estimate = 3.4%). The mean difference between the automated contour tracking and manual methods was -0.8% +/- 7.1%. In conclusion, a newly developed automated contour tracking method correlates highly with the manual method for the estimation of left ventricular cavity areas and fractional area change in high-quality images. This suggests that this new technique may be useful in the automated quantitation of left ventricular function in patients with high-quality images with no dropout and no intercavity artifact or structure.

Abstract:   Endoscopic surgery, also called minimally invasive surgery, is presumed drastically to reduce postoperative morbidity and thus to offer both human and economic benefits. For the surgeon, however, this approach leads to a number of gestural challenges that require extensive training to be mastered. In order to replace experimentation on animals and patients, we developed a simulator for endoscopic surgery. To achieve this goal, a first step was to develop a working prototype, a ''standard patient,'' on which the informatic and microengineering tools could be validated. We used the visible man dataset for this purpose. The external shape of the Visible man's liver, his biliary passages, and his extrahepatic portal system turned out to be fully within the standard pattern of normal anatomy. Anatomic Variations were observed in the intrahepatic right portal vein, the hepatic veins, and the arterial blood supply to the liver. Thus, the visible man dataset reveals itself to be well suited for the simulation of minimally invasive surgical operation such as endoscopic cholecystectomy. (C) 1997 Wiley-Liss, Inc.

Abstract:   This paper describes how the concept of imposing geometric constraints by minimizing cost functions may be used and extended to accomplish a variety of animated modelling tasks for computer graphics. In this approach a complex 3-D geometric problem is mapped into a scalar minimization formulation. The mapping provides a straightforward method for converting abstract geometric concepts into a construct that is easily computed, The minimization approach is demonstrated in three application areas: computer animation, visualization, and physically-based modelling. In the computer animation application, cost minimization may be used to generate motion paths and joint parameters for animated actors. The approach may also be used to generate deformable models that extract closed 3-D geometric models from volume data for visualization, In the final application, the approach provides the fundamental structure to a physically-based model of woven cloth. (C) 1997 John Wiley & Sons, Ltd.

Abstract:   Deformable geometric models can be used in the context of Bayesian analysis to solve ill-posed tomographic reconstruction problems. The uncertainties associated with a Bayesian analysis may be assessed by generating a set of random samples from the posterior, which may be accomplished using a Markov Chain Monte Carlo (MCMC) technique. We demonstrate the combination of these techniques for a reconstruction of a two-dimensional object from two orthogonal noisy projections. The reconstructed object is modeled in terms of a deformable geometrically defined boundary with a uniform interior density yielding a nonlinear reconstruction problem. We show how an MCMC sequence can be used to estimate uncertainties in the location of the edge of the reconstructed object. (C) 1997 John Wiley & Sons, Inc.

Abstract:   We address the problem of obtaining dense surface information from a sparse set of 3D data in the presence of spurious noise samples. The input can be in the form of points, or points with an associated tangent or normal, allowing both position and direction to be corrupted by noise. Most approaches treat the problem as an interpolation problem, which is solved by fitting a surface such as a membrane or thin plate to minimize some function. We argue that these physical constraints are not sufficient, and propose to impose additional perceptual constraints such as good continuity and ''cosurfacity.'' These constraints allow us to not only infer surfaces, but also to detect surface orientation discontinuities, as well as junctions, all at the same time. The approach Imposes no restriction on genus, number of discontinuities, number of objects, and is noniterative. The result is in the form of three dense saliency maps for surfaces, intersections between surfaces (i.e., 3D curves), and 3D junctions, respectively. These saliency maps are then used to guide a ''marching'' process to generate a description (e.g., a triangulated mesh) making information about surfaces, space curves, and 3D junctions explicit. The traditional marching process needs to be refined as the polarity of the surface orientation is not necessarily locally consistent. These three maps are currently not integrated, and this is the topic of our ongoing research. We present results on a variety of computer-generated and real data, having varying curvature, of different genus, and multiple objects.

Abstract:   A framework for object segmentation in vector-valued images is presented in this paper. The first scheme proposed is based on geometric active contours moving toward the objects to be detected in the vector-valued image. Object boundaries are obtained as geodesics or minimal weighted-distance curves, where the metric is given by a definition of edges in vector-valued data. The curve flow corresponding to the proposed active contours holds formal existence, uniqueness, stability, and correctness results. The scheme automatically handles changes in the deforming curve topology. The technique is applicable, for example, to color and texture images as well as multiscale representations. We then present an extension of these vector active contours, proposing a possible image flow for vector-valued image segmentation. The algorithm is based on moving each one of the image level sets according to the proposed vector active contours. This extension also shows the relation between active contours and a number of partial-differential-equations-based image processing algorithms as anisotropic diffusion and shock filters. (C) 1997 Academic Press.

Abstract:   We have developed several theorems for the detection of parallel curves in the continuous space. In this paper, we studied issues in carrying the continuous algorithm to the discrete case and also the perceptual characteristics leading to human recognition of parallelism. By formulating these properties in terms of several distinctive forces, we developed a force-driven model as a new optimization strategy to perform correspondence establishment between points in the matching curves. This force-driven mechanism provides a good coupling (or correspondence matching) result, which is the prerequisite for the correct detection of parallelism between curves. Convergence of the algorithm and implementation efficiency are also investigated and discussed. Experimental results on the relative weightings of these forces also shed light on the perceptual priority imposed by the human vision system. (C) 1997 Academic Press.

Abstract:   Subpixel methods that locate curves and their singularities, and that accurately measure geometric quantities, such as orientation and curvature, are of significant importance in computer vision and graphics. Such methods often use local surface fits or structural models for a local neighborhood of the curve to obtain the interpolated curve. Whereas their performance is good in smooth regions of the curve, it is typically poor in the vicinity of singularities. Similarly, the computation of geometric quantities is often regularized to deal with noise present in discrete data. However, in the process, discontinuities are blurred over, leading to poor estimates at them and in their vicinity. In this paper we propose a geometric interpolation technique to overcome these limitations by locating curves and obtaining geometric estimates while (1) not blurring across discontinuities and (2) explicitly and accurately placing them, The essential idea is to avoid the propagation of information across singularities. This is accomplished by a one-sided smoothing technique, where information is propagated from the direction of the side with the ''smoother'' neighborhood. When both sides are nonsmooth, the two existing discontinuities are relieved by placing a single discontinuity, or shock. The placement of shacks is guided by geometric continuity constraints, resulting in subpixel interpolation with accurate geometric estimates. Since the technique was originally motivated by curve evolution applications, we demonstrate its usefulness in capturing not only smooth evolving curves, but also ones with orientation discontinuities. In particular, the technique is shown to be far better than traditional methods when multiple or entire curves are present in a very small neighborhood. (C) 1997 Academic Press.

Abstract:   Until now, most optical pattern recognition filters have been designed to process one image at a time. However, in image sequences, successive frames are highly correlated, so that it is useful to take this correlation into account while designing the filter. We develop a target tracking processor following this method. The images are assumed to consist of a moving object appearing against a moving background. A model that takes into account two successive frames is designed. From this model we determine the maximum-likelihood processor for tracking the object from one frame to the next. Since this processor is based on correlation operations, it could be implemented on a hybrid optoelectronic system that makes use of the rapidity of optical correlation. (C) 1997 Optical Society of America.

Abstract:   In this paper we describe a feature-based approach to object recognition. The correspondence problem is solved by optimization of an energy function. While similar approaches suffer from local minima, we derive an energy function suitable for minimizing by deterministic annealing. Hereby global optimization can be achieved. Algorithms matching model features to image features in a coarse-to-fine manner are described. (C) 1997 Elsevier Science B.V.

Abstract:   This paper presents a general framework for image-based analysis of 3D repeating motions that addresses two limitations in the state of the art. First, the assumption that a motion be perfectly even from one cycle to the next is relaxed. Real repeating motions tend not to be perfectly even, i.e., the length of a cycle varies through time because of physically important changes in the scene. A generalization of period is defined for repeating motions that makes this temporal variation explicit. This representation, called the period trace, is compact and purely temporal, describing the evolution of an object or scene without reference to spatial quantities such as position or velocity. Second, the requirement that the observer be stationary is removed. Observer motion complicates image analysis because an object that undergoes a 3D repeating motion will generally not produce a repeating sequence of images. Using principles of affine invariance, we derive necessary and sufficient conditions for an image sequence to be the projection of a 3D repeating motion, accounting for changes in viewpoint and other camera parameters. Unlike previous work in visual invariance, however, our approach is applicable to objects and scenes whose motion is highly non-rigid. Experiments on real image sequences demonstrate how the approach may be used to detect several types of purely temporal motion features, relating to motion trends and irregularities. Applications to athletic and medical motion analysis are discussed.

Abstract:   We propose a snake-based approach that allows a user to specify only the distant end points of the curve he wishes to delineate without having to supply an almost complete polygonal approximation. This greatly simplifies the initialization process and yields excellent convergence properties. This is achieved by using the image information around the end points to provide boundary conditions and by introducing an optimization schedule that allows a snake to take image information into account first only near its extremities and then, progressively, toward its center. In effect, the snakes are clamped onto the image contour in a manner reminiscent of a ziplock being closed. These snakes can be used to alleviate the often repetitive task practitioners face when segmenting images by eliminating the need to sketch a feature of interest in its entirety, that is, to perform a painstaking, almost complete, manual segmentation.

Abstract:   This paper is a review of the use of contextual information in statistical image analysis. After defining what we mean by 'context', we describe the Bayesian approach to high-level image analysis using deformable templates. We describe important aspects of work on character recognition and syntactic pattern recognition; in particular, aspects of the work which are relevant to scene understanding. We conclude with a review of some work on knowledge-based systems which use context to aid object recognition.

Abstract:   We describe a system to detect the speaker's face and mouth in videophone sequences. A statistical scheme based on a subspace method is described for detecting and tracking faces under varying poses. A matching criterion based on a Generalized Likelihood Ratio is optimized efficiently with respect to a perspective transformation using a coarse-to-fine search strategy combined with a simulated annealing algorithm. Moreover, we analyze the amplitude projections around the speaker's mouth to describe the shape of the lips. All computations are performed on lossy H263-coded images, The proposed algorithms are well-suited to a further real-time implementation. (C) 1997 Elsevier Science B.V.

Abstract:   In this paper we present new methods to simultaneously extract and exploit the three-dimensional shape of a face and its surface texture. It is based on an active technique, i.e. special illumination, but in contrast to traditional active sensing does not require scanning or sequential projection of multiple patterns. This one-shot nature of the devise allows to capture moving objects, e.g. for making a 3D reconstruction of a face even when the person is talking. The use of the system is illustrated using simple methods to extract both textural and geometrical features from faces, that can be used for authentication purposes. The advantage of using 3D data is that both types of features can be made more invariant under changes in head pose or illumination conditions.

Abstract:   This paper describes an image metamorphosis technique to handle scattered feature constraints specified with points, polylines, and splines. Solutions to the following three problems are presented: feature specification, warp generation, and transition control. We demonstrate the use of snakes to reduce the burden of feature specification. Next, we propose the use of multilevel free-form deformations (MFFD) to compute C-2-continuous and one-to-one mapping functions among the specified features. The resulting technique, based on B-spline approximation, is simpler and faster than previous warp generation methods. Furthermore, it produces smooth image transformations without undesirable ripples and foldovers. Finally, we simplify the MFFD algorithm to derive transition functions to control geometry and color blending. Implementation details are furnished and comparisons among Various metamorphosis techniques are presented.

Abstract:   We present a scheme for reliable and accurate surface reconstruction from stereoscopic images containing only fine texture and no stable high-level features. Partial shape information is used to improve surface computation: first by fitting an approximate, global, parametric model, and then by refining this model via local correspondence processes. This scheme eliminates the window size selection problem in existing area-based stereo correspondence schemes, These ideas are integrated in a practical vision system that is being used by environmental scientists to study wind erosion of bulk material such as coal ore being transported in open rail cars.

Abstract:   Accurate segmentation of medical images poses one of the major challenges in computer vision. Approaches that rely solely on intensity information frequently fail because similar intensity values appear in multiple structures. This paper presents a method for using shape knowledge to guide the segmentation process, applying it to the task of finding the surface of the brain. A 3-D model that includes local shape constraints is fitted to an MR volume dataset. The resulting low-resolution surface is used to mask out regions far from the cortical surface, enabling an isosurface extraction algorithm to isolate a more detailed surface boundary. The surfaces generated by this technique are comparable to those achieved by other methods, without requiring user adjustment of a large number of ad hoc parameters.

Abstract:   We propose a method for the 3D segmentation and representation of cortical folds with a special emphasis on the cortical sulci. These cortical structures are represented using "active ribbons". Active ribbons are built from active surfaces, which represent the median surface of a particular sulcus filled by CSF. Sulci modeling is obtained from MRI acquisitions (usually T1 images). The segmentation is performed using an automatic labeling procedure to separate gyri from sulci based on curvature analysis of the different iso-intensity surfaces of the original MRI volume. The outer parts of the sulci are used to initialize the convergence of the active ribbon from the outer parts of the brain to the interior. This procedure has two advantages: first, it permits the labeling of voxels belonging to sulci on the external part of the brain as well as on the inside (which is often the hardest point) and secondly, this segmentation allows 3D visualization of the sulci in the MRI volumetric environment as well as showing the sophisticated shapes of the cortical structures by means of isolated surfaces. Active ribbons can be used to study the complicated shape of the cortical anatomy, to model the variability of these structures in shape and position, to assist nonlinear registrations of human brains by locally controlling the warping procedure, to map brain neurophysiological functions into morphology or even to select the trajectory of an intra-sulci (virtual) endoscope.

Abstract:   Surgical simulation increasingly appears to be an essential aspect of tomorrow's surgery The development of a hepatic surgery simulator is an advanced concept calling for a new writing system which will transform the medical world. virtual reality: Virtual reality extends the perception of our five senses by representing more than rite real state of things by the means of computer sciences and robotics. It consists of three concepts : immersion, navigation and interaction. Three reasons have led tts to develop this simulator: the first:rt is to provide the surgeon with a comprehensive visualisation of the organ. The second reason is to allow for planning and surgical simulation that could be compared with the detailed flight-plan for a commercial jet pilot. The third lies in the fact that virtual reality is an integrated part of the concept of computer assisted surgical procedure. The project consists of a sophisticated simulator which has to include five requirements, : visual fidelity: interactivity: physical properties, physiological properties, sensory input and output. In this report we will describe how to get a realistic 3D model of the liver from bi-dimensional 2D medical images for anatomical and surgical training. The introduction of a tumor and the consequent planning and virtual resection is also described as are force feedback and real-time interaction.

Abstract:   We describe a fully automatic three-dimensional (3-D)-segmentation technique for brain magnetic resonance (MR) images, By means of Markov random fields (MRF's) the segmentation algorithm captures three features that are of special importance for MR images, i.e., nonparametric distributions of tissue intensities, neighborhood correlations, and signal inhomogeneities, Detailed simulations and real MR images demonstrate the performance of the segmentation algorithm, In particular, the impact of noise, inhomogeneity, smoothing, and structure thickness are analyzed quantitatively, Even single-echo MR images are well classified into gray matter, white matter, cerebrospinal fluid, scalp-bone, and background, A simulated annealing and an iterated conditional modes implementation are presented.

Abstract:   Edge linking is a fundamental computer vision task, yet presents difficulties arising from the lack of information in the image. Viewed ns a constrained optimisation problem, it is NP hard - being isomorphic to the classical travelling salesman problem. Self-learning neural techniques boast the ability to solve hard, ill-defined problems, and hence offer promise for such an application, This paper examines the suitability of four well-known unsupervised techniques for rite task of edge linking, by applying them to a test bed of edge point images and then evaluating their performance both quantitatively and qualitatively. Techniques studied are the elastic net, active contours, Kohonen map and Burr's modified elastic net. Of these, only the elastic ner and the Kohonen map are realistic contenders for general edge-linking tasks. However, the other two exhibit behaviour which may make them particularly suited to some specific image-processing and computer vision applications.

Abstract:   The problem of texture recognition is addressed by studying appropriate descriptors in the spatial frequency domain. During a training phase a filter is configured to determine different classes of texture by the response of its correlation with the Fourier spectrum of training-image templates. This is achieved by genetic algorithm-based optimisation. The technique is tested on standard texture patterns and then applied to magnetic resonance images of the brain to segment the cerebellum from the surrounding white and grey matter. Comparisons with established texture recognition techniques are presented, which show that the proposed method performs as well as, or better than, traditional techniques for the chosen instances of standard and anatomical texture and has the advantage of not having to decide which texture measure to use for a specific image structure. (C) 1997 Elsevier Science B.V.

Abstract:   Spatial Reasoning, reasoning about spatial information (i.e. shape end spatial relations), is a crucial function of image understanding and computer vision systems. This paper proposes a novel spatial reasoning scheme for image understanding and demonstrates its utility and effectiveness in two different systems: region segmentation and aerial image understanding systems. The scheme is designed based on a so-called Multi-Agent/Cooperative Distributed Problem Solving Paradigm, where a group of intelligent agents cooperate with each other to fulfill a complicated task. The first part of the paper describes a cooperative distributed region segmentation system, where each region in an image is regarded as an agent. Starting from seed regions given at the initial stage, region agents deform their shapes dynamically so that the image is partitioned into mutually disjoint regions. The deformation of each individual region agent is realized by the snake algorithm(14) and neighboring region agents cooperate with each other to find common region boundaries between them. In the latter part of the paper, we first give a brief description of the cooperative spatial reasoning method used in our aerial image understanding system SIGMA. In SIGMA, each recognized object such as a house and a road is regarded as an agent. Each agent generates hypotheses about its neighboring objects to establish spatial relations and to detect missing objects. Then, we compare its reasoning method with that used in the region segmentation system. We conclude the paper by showing further utilities of the Multi-Agent/Cooperative Distributed Problem Solving Paradigm for image understanding.

Abstract:   Active or deformable models have emerged as a popular modelling paradigm in computer vision. These models have the flexibility to adapt themselves to the image data, offering the potential for both generic object recognition and non-rigid object tracking. Because these active models are underconstrained, however, deformable shape recovery often requires manual segmentation or good model initialization, while active contour trackers have been able to track only an object's translation in the image. In this paper, we report our current progress in using a part-based aspect graph representation of an object(14) to provide the missing constraints on data-driven deformable model recovery and tracking processes.

Abstract:   In previous work we have modeled simple 3D anatomical objects using deformed superquadrics and established their optimal position with the aid of genetic algorithms (GAs). Here we extend the complexity of the search object using 3D Fourier descriptor (FD) representations and allow GAs once again to optimize the object's shape and position. Using magnetic resonance image data, we perform an approximate segmentation on one lateral ventricle in the brain and use the FDs from this as seeding values for the GAs to search for the left and right lateral ventricles in seven 3D data sets. We show that the method is capable of coping with normal biological variation. Finally, we compare FD/GA-guided segmentation with a manually guided interactive region growing method and find an agreement of 78 +/- 10% in voxel classification with a corresponding average edge placement error of 2.2 +/- 0.4 mm. (C) 1997 Academic Press.

Abstract:   We address the problem of localizing objects using color, texture and shape. Given a handrawn sketch for querying an object shape, and its color and texture, the algorithm automatically searches the database images for objects which meet the query attributes. The database images do not need to be presegmented or annotated. The proposed algorithm operates in two stages. In the first stage, we use local texture and color features to find a small number of candidate images, and identify regions in the candidate images which share similar texture and color as the query example. To speed up the processing, the texture and color features are directly extracted from the Discrete Cosine Transform (DCT) compressed domain. In the second stage, we use a deformable template matching method to match the query shape to the image edges at the locations which possess the desired texture and color attributes. This algorithm is different from the other content-based image retrieval algorithms in that: (i) no presegmentation of the database images is needed, and (ii) the color and texture features are directly extracted from the compressed images. Experimental results show that substantial computational savings can be achieved utilizing multiple image cues.

Abstract:   We propose an automated approach to modeling drainage channels-and, more generally, linear features that lie on the terrain-from multiple images, which results not only in high-resolution, accurate and consistent models of the features, but also of the surrounding terrain. In our specific case, we have chosen to exploit the fact that rivers flow downhill and lie at the bottom of local depressions in the terrain, valley floors tend to be "U" shaped, and the drainage pattern appears as a network of linear features that can be visually detected in single gray-level images. Different approaches have explored individual facets of this problem. Ours unifies these elements in a common framework. We accurately model terrain and features as 3-dimensional objects from several information sources that may be in error and inconsistent with one another. This approach allows us to generate models that are faithful to sensor data, internally consistent and consistent with physical constraints. We have proposed generic models that have been applied to the specific task at hand-river delineation and data elevation model (DEM) refinement-and show that the constraints can be expressed in a computationally effective way and, therefore, enforced while initializing the models and then fitting them to the data. We will also argue that the same techniques are robust enough to work on other features that are constrained by predictable forces.

Abstract:   Synthetic aperture radar (SAR) images are notoriously difficult to interpret. Segmentation is simplified if a digital map is available, to which the image can be registered. Also, registration is simplified if a digital elevation model (DEM) is available. In this paper it is shown that, if a DEM is unavailable, it can be estimated by minimising an energy functional consisting of a measure of agreement between the SAR image and a digital map together with a thin-plate bending-energy term. A computationally-efficient, finite-element algorithm is proposed to solve the optimisation problem. The method is applied to automatically align an airborne SAR image with a digital map of field boundaries, producing an image which is simultaneously registered and segmented.

Abstract:   We describe a robust method for locating and tracking lips in gray-level image sequences. Our approach learns patterns of shape variability from a training set which constrains the model during image search to only deform in ways similar to the training examples, Image search is guided by a learned gray-level model which is used to describe the large appearance variability of lips, Such variability might be due to different individuals, illumination, mouth opening, specularity, or visibility of teeth and tongue, Visual speech features are recovered from the tracking results and represent both shape and intensity information, We describe a speechreading (lip-reading) system, where the extracted features are modeled by Gaussian distributions and their temporal dependencies by hidden Markov models. Experimental results are presented for locating lips, tracking lips, and speechreading. The database used consists of a broad variety of speakers and was recorded in a natural environment with no special lighting or lip markers used, For a speaker independent digit recognition task using visual information only, the system achieved an accuracy about equivalent to that of untrained humans. (C) 1997 Academic Press.

Abstract:   An approach is presented for imposing generic hard constraints an deformable models at a low computational cost, while preserving the good convergence properties of snake-like models. We believe this capability to be essential not only for the accurate modeling of individual objects that obey known geometric and semantic constraints but also for the consistent modeling of sets of objects. Many of the approaches to this problem that have appeared in the vision literature rely on adding penalty terms to the objective functions. They rapidly become intractable when the number of constraints increases, Applied mathematicians have developed powerful constrainted optimization algorithms that, in theory, can address this problem. However, these algorithms typically do not take advantage of the specific properties of snakes, We have therefore designed a new algorithm that is closely related to Lagrangian methods but is tailored to accommodate the particular brand of deformable models used in the image understanding community, We demonstrate the validity of our approach first in two dimensions using synthetic images and then in three dimensions using real aerial images to simultaneously model terrain, roads, and ridgelines under consistency constraints. (C) 1997 Academic Press.

Abstract:   This work applies 3D Fourier Descriptors (FDs) and Genetic Algorithms (GAs) to the optimisation of the shape and position of models of anatomical objects within the human brain. Using magnetic resonance image data, we perform an approximate segmentation on one lateral ventricle and use the FDs from this as seeding values for the GAs to search for the left and right lateral ventricles in subsequent 3D image data sets, showing that the method is capable of coping with normal biological variation within and between individuals. Finally, we compare the GA-guided segmentation with a manual region growing method and find an agreement of 79.9+/-5.8% in voxel classification with a corresponding mean edge placement error of 2.1+/-0.4 mm. Copyright (C) 1997 Pattern Recognition Society.

Abstract:   Computer vision has emerged as a challenging and important area of research, both as an engineering and a scientific discipline. The growing importance of computer vision is evident from the fact that it was identified as one of the ''Grand Challenges'' and also from its prominent role in the National Information Infrastructure. While the design of a general purpose vision system continues to be elusive, machine vision systems are being used successfully in specific application domains. Building a practical vision system requires a careful selection of appropriate sensors, extraction and integration of information from available cues in the sensed data, and evaluation of system robustness and performance. We discuss and demonstrate advantages of (i) multi-sensor fusion, (ii) combination of features and classifiers, (iii) integration of visual modules, and (iv) admissibility and goal-directed evaluation of vision algorithms. The requirements of several prominent real world applications such as biometry, document image analysis, image and video database retrieval, and automatic object model construction offer exciting problems and new opportunities to design and evaluate vision algorithms. Copyright (C) 1997 Pattern Recognition Society.

Abstract:   In this note, we employ the new geometric active contour models formulated in [25] and [26] for edge detection and segmentation of magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound medical imagery, Our method is based on defining feature-based metrics on a given image which in turn leads to a novel snake paradigm in which the feature of interest mag be considered to lie at the bottom of a potential well, Thus, the snake is attracted very quickly and efficiently to the desired feature.

Abstract:   A novel scheme for the detection of object boundaries is presented. The technique is based on active contours evolving in time according to intrinsic geometric measures of the image. The evolving contours naturally split and merge, allowing the simultaneous detection of several objects and both interior and exterior boundaries. The proposed approach is based on the relation between active contours and the computation of geodesics or minimal distance curves. The minimal distance curve lays in a Riemannian space whose metric is defined by the image content. This geodesic approach for object segmentation allows to connect classical ''snakes'' based on energy minimization and geometric active contours based on the theory of curve evolution. Previous models of geometric active contours are improved, allowing stable boundary detection when their gradients suffer from large variations, including gaps. Formal results concerning existence, uniqueness, stability, and correctness of the evolution are presented as well. The scheme was implemented using an efficient algorithm for curve evolution. Experimental results of applying the scheme to real images including objects with holes and medical data imagery demonstrate its power. The results may be extended to 3D object segmentation as well.

Abstract:   PURPOSE: The authors evaluated computed tomographic (CT) virtual colography for the detection of simulated polyps under ideal conditions, as well as the effects on lesion conspicuity of (a) collimation, (b) table pitch, and (c) orientation of the colon lumen with respect to the gantry. MATERIALS AND METHODS: Pig colon was resected and cleansed, and polyps with diameters of 3, 7, and 10 mm were created. Each specimen was scanned with collimation of 5 and 7 mm and table pitch of 1.0, 1.6, and 2.0 at angles of 0 degrees, 45 degrees, and 90 degrees to the gantry. The initial two-dimensional (2D) images were reconstructed at 1-mm intervals (2D reconstructions), from which three-dimensional (3D) virtual colography images were generated. Polyp conspicuity on the initial and reconstructed 2D images and the 3D reconstructions was evaluated on a three-point scale: 0 = polyp not depicted, 1 = polyp faintly depicted, and 2 = polyp clearly depicted. RESULTS: The 10-mm-diameter polyp was clearly depicted (grade 2 conspicuity) on every initial and reconstructed 2D image and 3D reconstruction without regard to collimation, table pitch, or angle to the gantry. The 7-mm-diameter polyp was clearly depicted (grade 2 conspicuity) on every initial and reconstructed 2D image, but conspicuity on 3D reconstructions varied as the imaging parameters varied. The 3-mm-diameter polyp was faintly depicted (grade 1 conspicuity) on the initial and reconstructed 2D images and 3D reconstructions, but conspicuity varied on the 3D reconstructions as the imaging parameters varied. CONCLUSION: CT virtual colography helped detection of small mucosal polyps regardless of the angle of the colon lumen to the gantry at which they were obtained.

Abstract:   A multilevel Markov Random Field (MRF) energy environment has been developed that simultaneously performs delineation, representation and classification of two-dimensional objects by using a global optimization technique. This environment supports a multipolar shape representation which establishes a dynamic MRF structure. This structure is initialized as a single-center polar representation, and uses minimum description length tests to determine whether to establish new polar centers. The polar representations at these centers are compared with a database of such representations in order to identify pieces of objects, and the results of these comparisons are used to compile evidence for global object identifications. This method is potentially more robust than conventional multistaged approaches to object recognition because it incorporates all the information about the objects into a single adaptive decision process, and its use of a multipolar representation allows it to handle partially occluded objects.

Abstract:   We propose an improved method for eye-feature extraction, descriptions, and tracking using deformable templates. Some existing algorithms are exploited to locate the initial position of eye features and then deformable templates are used for extracting and describing the eye features. Rather than using original energy minimization for matching the templates, the region-based approach is proposed for template deformation. Based on the region properties, the new strategy avoids problems such as template shrinking, adjusting the weights of energy terms, failure of orientation adjustment due to some exceptional cases. Our strategies are also coupled with Canny edge operator to give a new back-end processing. By integrating the local edge information from the edge detection and the global collector from our region-based template deformation, this processing stage can generate accurate eye-feature descriptions. Finally, the template deformation process is applied to tracking eye features. (C) 1997 Pattern Recognition Society.

Abstract:   Video provides a comprehensive visual record of environment activity over time. Thus, video data is an attractive source of information for the creation of virtual worlds which require some real-world fidelity. This paper describes the use of multiple streams of video data for the creation of immersive virtual environments. We outline our multiple perspective interactive video (MPI-Video) architecture which provides the infrastructure for the processing and analysis of multiple streams of video data. Our MPI-Video system performs automated analysis of the raw video and constructs a model of the environment and object activity within this environment. This model provides a comprehensive representation of the world monitored by the cameras which, in turn, can be used in the construction of a virtual world. In addition, using the information produced and maintained by the MPI-Video system; our immersive video system generates virtual video sequences. These are sequences of the dynamic environment from an arbitrary view point generated using the real camera data. Such sequences allow a user to navigate through the environment and provide a sense of immersion in the scene. We discuss results from our MPI-Video prototype, outline algorithms for the construction of virtual views and provide examples of a variety of such immersive video sequences.

Abstract:   Calculation of global cardiac function parameters has been validated using fast, segmented k-space, breath-hold, gradient-echo, magnetic resonance images. Images of phantoms, experimental animals, normal volunteers, and patients were acquired with a 1.5 T clinical scanner, Humans were imaged using two phased-array surface coils in multicoil mode, Myocardial contours were extracted using a new interactive, semi-automated method based on the active contour model method, Images were acquired in the short-axis orientation, and, using a new imaging and analysis strategy, in rotating plane long-axis orientations, to provide better definition of the valve planes and the apex, and also to reduce the number of slices (compared with the short-axis method) required to sample the whole heart, Validation was accomplished through calculation of the volumes of phantoms and left and right ventricular masses of animal hearts. Functional parameters from MRI were compared with those from echocardiograms and radionuclide angiograms in normal volunteers and patients, respectively.

Abstract:   We propose in this paper a snake-based segmentation processor to track the shape of a target with random white intensity appearing on a random white spatially disjoint background. We study the optimal solution for Gamma laws and we discuss the relevance of such statistics for realistic situations. This algorithm, based on an active contour model (snakes), consists in correlations of a binary reference with the scene image or with pre-processed version of the scene image. This method is a generalization of correlation techniques and thus opens new applications for digital and optical correlators.

Abstract:   A geometric approach for 3D object segmentation and representation is presented. The segmentation is obtained by deformable surfaces moving towards the objects to be detected in the 3D image. The model is based on curvature motion and the computation of surfaces with minimal areas, better known as minimal surfaces. The space where the surfaces are computed is induced from the 3D image (volumetric data) in which the objects are to be detected. The model links between classical deformable surfaces obtained via energy minimization, and intrinsic ones derived from curvature based flows. The new approach is stable, robust, and automatically handles changes in the surface topology during the deformation.

Abstract:   The current methods of training medical personnel to provide emergency medical care have several important shortcomings. For example, in the training of wound debridement techniques, animal models are used to gain experience treating traumatic injuries. We propose an alternative approach by creating a three-dimensional, interactive computer model of the human body that can be used within a virtual environment to learn and practice wound debridement techniques and Advanced Trauma Life Support (ATLS) procedures. As a first step, we have developed a computer model that represents the anatomy and physiology of a normal and injured lower limb. When visualized and manipulated in a virtual environment, this computer model will reduce the need for animals in the training oi-trauma management and potentially provide a superior training experience. This article describes the development choices that were made in implementing the preliminary system and the challenges that must be met to create an effective medical training environment.

Abstract:   An image database search method is described that uses strain energy from prototypes to represent shape categories. Rather than directly comparing a candidate shape with all entries in a database, shapes are ordered in terms of non-rigid deformations that relate them to a small subset of representative prototypes. Shape correspondences are obtained via modal matching, a decomposition for matching, describing, and comparing shapes despite sensor variations and non-rigid deformations. Deformation is decomposed into an ordered basis of orthogonal principal components. This allows selective invariance to in-plane rotation, translation, and scaling, and quasi-invariance to affine deformations. Retrieval accuracy and stability are evaluated in experiments with 2-D image databases. (C) 1997 Pattern Recognition Society.

Abstract:   Optimization processes based on ''active models'' play central roles in many areas of computational vision as well as computational geometry. Unfortunately, current models usually require highly complex and sophisticated mathematical machinery and at the same time they suffer from a number of limitations which impose restrictions on their applicability. In this paper a simple class of discrete active models, called migration processes (MPs), is presented. The processes are based on iterated averaging over neighborhoods defined by constant geodesic distance. It is demonstrated that the MP model-a system of self-organizing active particles-has a number of advantages over previous models, both parametric active models (''snakes'') and implicit (contour evolution) models. Due to the generality of the MP model, the process can be applied to derive natural solutions to a variety of optimization problems,including defining (minimal) surface patches given their boundary curves; finding shortest paths joining sets of points; and decomposing objects into ''primitive'' parts. (C) 1997 Pattern Recognition Society.

Abstract:   A scheme employing one-dimensional (1-D) Regularized Cubic B-Spline (RCBS) fitting [G. Chen and Y. H. Yang, IEEE Trans. Systems Man Cybernet. 25, 636-693 (1995)] has been used successfully in the task of step edge detection. The regularized fitting is transformed into a quadratic energy equation to simplify the computation. This scheme, however, has three major limitations: it is non-linear, has a limited accuracy and is computationally expensive. This paper presents a modified scheme which overcomes these limitations. The modified scheme employs the I-D RCBS fitting on the horizontal and Vertical orientations of a window of an image to generate two I-D signals, which provide sufficient information about the local property of the sub-image for roof edge detection. Experimental results show that the scheme of roof edge detection is very sensitive to small signals. (C) 1997 Pattern Recognition Society.

Abstract:   Oceanic temperature fronts observed through composite infrared images from the AVHRR satellite data are fragmented due mostly to cloud occlusion. The sampling frequency of such frontal position observations tends to be insufficiently high to resolve dynamics of the meandering features associated with the frontal contour, so that contour reconstruction using a standard space-time smoothing often leads to introduction of spurious features. Augmenting space-time smoothing with a simple point-feature detection/matching scheme, however, can dramatically improve the reconstruction product, This paper presents such a motion-compensated interpolation algorithm, for reconstruction of open contours evolving in time given fragmented position data, The reconstruction task is formulated as an optimization problem, and a time-sequential solution which adaptively estimates feature motion is provided. The resulting algorithm reliably interpolates position measurements of the surface temperature fronts associated with the highly convoluted portions of strong ocean currents such as the Gulf Stream and Kuroshio.

Abstract:   An automatic segmentation method has been developed for cardiovascular multimodality imaging. A ''snake'' model based on a curve shaping and an energy-minimizing process is used to detect blood-wall interfaces on Cine-CT, MRI and ultrasound images. Deformation of a reduced set of contour points was made according to a discretized global, regional and local minimum energy criterion. A continuous regional optimization process was also integrated into the deformation model, it takes into account a cubic spline interpolation and adaptive regularity constraints. The constraints provided rapid convergence toward a final contour position by successively stopping spline segments. (C) 1997 Elsevier Science Ltd.

Abstract:   It is widely recognized that automatic segmentation is hard, leading to the state where user intervention cannot be avoided. In this paper we review existing literature and propose a systematic approach for the integration of automatic and interactive segmentation methods into one unified process. A framework and requirements for intelligent interactive segmentation are formulated, and an example is presented.

Abstract:   Robust segmentation of normal anatomical objects in medical images requires (1) methods for creating object models that adequately capture object shape and expected shape variation across a population, and (2) methods for combining such shape models with unclassified image data to extract modeled objects. Described in this paper is such an approach to model-based image segmentation, called deformable shape loci (DSL), that has been successfully applied to 2D MR slices of the brain ventricle and CT slices of abdominal organs. The method combines a model and image data by warping the model to optimize an objective function measuring both the conformation of the warped model to the image data and the preservation of local neighbor relationships in the model. Methods for forming the model and for optimizing the objective function are described.

Abstract:   A major problem with many current techniques in medical imaging is the sheer volume of data of the results; examples are in spiral CT, MRI especially functional imaging, SPECT and PET. In general the data are n-D, often 3-D plus time. Such data are hard to visualise without compression, specifically some kind of multi-dimensional projection to reduce dimensionality, for example reducing the n-D to a 2-D image. Both linear and non-linear operations can be considered, and two classes of method are important: data driven and hypothesis driven. Illustrative of data driven methods is principal component analysis (and factor analysis) where from the statistical aim of reducing correlation, axes in the multi-dimensional space can be defined for the projection operation. Unfortunately, in practice, a pure statistical method does not generally map well on to expected physiological functions (or models), and some kind of oblique rotation is required, based on the choice of appropriate constraints such as that of positivity. Hypothesis driven methods are all implicitly or explicitly based on models. Thus associating data driven and hypothesis driven ap preaches leads to constrained statistical data (image) processing. Examples are shown as used in nuclear medicine and MRI. Another important problem considered is that of multi-modality image registration and fusion. Although many methods exist, all based on the minimization of an appropriate distance functions between two image data sets, additional constraints are required when the images are not too similar. This leads to the idea of using mutual information as a distance measure, and imposing constraints by means of cluster analysis of the n-dimensional feature space. Finally, in the analysis of such data, tests against reference data sets (atlases) are required, normally requiring warping the data sets in space, for example by the use of optic flow, or some kind of diffusion equation. Again, the boundary values for the method need to be defined with respect to medical knowledge, a further good example of data driven algorithms supervised using clinical constraints or models.

Abstract:   A conventional active contour formulation suffers difficulty in appropriate choice of an initial contour and values of parameters. Recent approaches have aimed to resolve these problems but can compromise other performance aspects. To relieve the problem in initialization, we use a dual active contour, which is combined with a local shape model to improve the parameterization. One contour expands from inside the target feature, the other contracts from the outside. The two contours are interlinked to provide a balanced technique with an ability to reject ''weak'' local energy minima.

Abstract:   In this paper a new formulation of the two-dimensional (2-D) deformable template matching problem is proposed. It uses a lower-dimensional search space than conventional methods by precomputing extensions of the deformable template along orthogonal curves. The reduction in search space allows the use of dynamic programming to obtain globally optimal solutions and reduces the sensitivity of the algorithm to initial placement of the template, Further, the technique guarantees that the result is a curve which does not collapse to a point in the absence of strong image gradients and is always nonself intersecting. Examples of the use of the technique on real-world images and in simulations at low signal-to-noise ratios (SNR's) are also provided.

Abstract:   In this paper, we present a new approach for detection of brain tumor boundaries in medical images using a Hopfield neural network. The boundary detection problem is formulated as an optimization process that seeks the boundary points to minimize an energy functional based on an active contour model, A modified Hopfield network is constructed to solve the optimization problem, Taking advantage of the collective computational ability and energy convergence capability of the Hopfield network, our method produces the results comparable to those of standard ''snakes''-based algorithms, but it requires less computing time, With the parallel processing potential of the Hopfield network, the proposed boundary detection can be implemented for real time processing, Experiments on different magnetic resonance imaging (MRI) data sets show the effectiveness of our approach.

Abstract:   We describe a computerized method to automatically find and label the cortical surface in three-dimensional (3-D) magnetic resonance (MR) brain images, The approach we take is to model a prelabeled brain atlas as a physical object and give it elastic properties, allowing it to warp itself onto regions in a preprocessed image. Preprocessing consists of boundary-finding and a morphological procedure which automatically extracts the brain and sulci from an MR image and provides a smoothed representation of the brain surface to which the deformable model can rapidly converge, Our deformable models are energy-minimizing elastic surfaces that can accurately locate image features, The models are parameterized with 3-D bicubic B-spline surfaces, We design the energy function such that cortical fissure (sulci) points on the model are attracted to fissure points on the image and the remaining model points are attracted to the brain surface, A conjugate gradient method minimizes the energy function, allowing the model to automatically converge to the smoothed brain surface, Finally, labels are propagated from the deformed atlas onto the high-resolution brain surface.

Abstract:   This paper describes a computer vision system for the automatic extraction and velocity measurement of moving leukocytes that adhere to microvessel walls from a sequence of images, The motion of these leukocytes can be visualized as motion along the wall contours, We use the constraint that the leukocytes move along the vessel wall contours to generate a spatiotemporal image, and the leukocyte motion is then extracted using the methods of spatiotemporal image analysis, The generated spatiotemporal image is processed by a special-purpose orientation-selective filter and a subsequent grouping process newly developed for this application. The orientation-selective filter is designed by considering the particular properties of the spatiotemporal image in this application in order to enhance only the traces of leukocytes. In the subsequent grouping process, leukocyte trace segments are selected and grouped among all the segments obtained by simple thresholding and skeletonizing operations, We show experimentally that the proposed method can stably extract leukocyte motion.

Abstract:   A novel image processing scheme for extracting the intracranial contours in axial magnetic resonance data sets is proposed. The scheme incorporates the method of active contour models, a recently introduced paradigm for contour extraction. Its performance is nearly ideal for T2-weighted images. Although the performances for proton-density-weighted images and T1-weighted images drop slightly, qualitatively satisfactory extraction still can be obtained for T1-weighted images. Due to high degree of automation, the scheme should help speed up some image processing applications that require the presegmentation of the intracranial cavity.

Abstract:   The segmentation of structure from images is an inherently difficult problem in computer vision and a bottleneck to its widespread application, e.g., in medical imaging, This paper presents an approach for integrating local evidence such as regional homogeneity and edge response to form global structure for figure-ground segmentation. This approach is motivated by a shock-based morphogenetic language, where the growth of four types of shocks results in a complete description of shape, Specifically, objects are randomly hypothesized in the form of fourth-order shocks (seeds) which then grow, merge, split, shrink, and, in general, deform under physically motivated ''forces,'' but slow down and come to a halt near differential structures. Two major issues arise in the segmentation of 3D images using this approach. First, it is shown that the segmentation of 3D images by 3D bubbles is superior to a slice-by-slice segmentation by 2D bubbles or by ''21/2D bubbles'' which are inherently 2D but use 3D information for their deformation. Specifically, the advantages lie in an intrinsic treatment of the underlying geometry and accuracy of reconstruction. Second, gaps and weak edges, which frequently present a significant problem for 2D and 3D segmentation, are regularized by curvature-dependent curve and surface deformations which constitute diffusion processes, The 3D bubbles evolving in the 3D reaction-diffusion space are a powerful tool in the segmentation of medical and other images, as illustrated for several realistic examples. (C) 1997 Academic Press.

Abstract:   Even though methods based on the use of deformable models have become prevalent, the quality of their output depends critically on the model's initial state, The issue of initializing such models, however, has not received much attention even though it is often key to the implementation of a truly useful system. We therefore present a new approach to segmentation of three-dimensional (3-D) shapes that initializes and then optimizes a 3-D surface model given only the data and a very small number of 3-D seed points and corresponding surface normals. This is a valuable capability for medical, robotic, and cartographic applications where such seed points can be naturally supplied, In effect, the surface model is clamped onto the object boundary in a manner reminiscent of Velcro being closed. Applications of the developed method to stereo imagery and to volumetric medical data are demonstrated. (C) 1997 Academic Press.

Abstract:   An understanding of a scene's causal physics-how scene elements interact and respond to forces-is a precondition to reasoning about how the scene came to be, how it may evolve in time, and how it will respond to manipulation. We propose a computationally inexpensive method for recovering causal structure from images, in which a scene model is built incrementally through interleaved sensing and analysis. Reasoning uses generic qualitative knowledge about rigid-body interactions, reusable between domains and similar to concepts thought to be acquired or activated during child development. Causal constraint propagation reveals anomalous degrees of freedom in the scene model; prediction yields sensory plans to resolve them, Sensing operations are highly directed and local in scope, e.g., visual routines and proprioception. Inference depth and the number of pixels ''touched'' are bounded by the complexity of the scene. We present algorithms and semantics that have been successfully reused in several domains of highly structured scenes; in particular we detail a vision system that reverse-engineers machines. (C) 1997 Academic Press.

Abstract:   We describe a novel technique for matching and recognition based on deformable intensity surfaces which incorporates both the shape (x, y) and the texture (I(x, y)) components of a 2D image. Specifically, the intensity surface is modeled as a deformable 3D mesh in (x, y, I(x, y)) space which obeys Lagrangian dynamics. Using an efficient technique for matching two surfaces (in terms of the analytic modes of vibration), we can obtain a dense correspondence field (or 3D warp) between two images, Furthermore, we use explicit statistical learning of the class of valid deformations in order to provide a priori knowledge about object-specific deformations, The resulting formulation leads to a compact representation based on the physically-based modes of deformation as well as the statistical modes of variation observed in actual training data. We demonstrate the power of this approach with experiments utilizing image matching, interpolation of missing data, and image retrieval in a large face database. (C) 1997 Academic Press.

Abstract:   We present a novel geometric approach for solving the stereo problem for an arbitrary number of images (greater than or equal to 2). It is based upon the definition of a variational principle that must be satisfied by the surfaces of the objects in the scene and their images. The Euler-Lagrange equations which are deduced from the variational principle provide a set of PDE's which are used to deform an initial set of surfaces which then move towards the objects to be detected. The level set implementation of these PDE's potentially provides an efficient and robust way of achieving the surface evolution and to deal automatically with changes in the surface topology during the deformation, i.e. to deal with multiple objects. Results of a two dimensional implementation of our theory are presented on synthetic and real images.

Abstract:   In this work we present a snake based approach for the segmentation of images of computerized tomography (CT) scans, We introduce a new term for the internal energy and another one for external energy which solve common problems associated with classical snakes in this type of images. A simplified minimizing method is also presented. (C) 1997 Elsevier Science B.V.

Abstract:   We have developed an algorithm for segmenting objects with closed, non-intersecting boundaries, such as the heart and the lungs, that is independent of the imaging modality used (e.g., MRI, CT, echocardiography). Our method is automatic and requires as initialization a single pixel/voxel within the boundaries of the object. Existing segmentation techniques either require much more information during initialization, such as an approximation to the object's boundary, or are not robust to the types of noisy data encountered in the medical domain. By integrating region-based and physics-based modeling techniques we have devised a hybrid design that overcomes these limitations. In our experiments we demonstrate across imaging modalities, that this integration automates and significantly improves the object boundary detection results. This paper focuses on the application of our method to 3D datasets.

Abstract:   We propose a methodology for extracting parametric representations of the cerebral sulci from magnetic resonance images, and we consider its application to two medical imaging problems: quantitative morphological analysis and spatial normalization and registration of brain images. Our methodology is based on deformable models utilizing characteristics of the cortical shape. Specifically, a parametric representation of a sulcus is determined by the motion of an active contour along the medial surface of the corresponding cortical fold. The active contour is initialized along the outer boundary of the brain, and deforms toward the deep edge of a sulcus under the influence of an external force field restricting it to lie along the medial surface of the particular cortical fold. A parametric representation of the surface is obtained as the active contour traverses the sulcus. In this paper we present results of this methodology and its applications.

Abstract:   The present study investigates the possibility to utilize Compton scatter data for registration of abdominal SPECT images. A method for registration to CT is presented, based on principal component analysis and cross-correlation of binary images representing the interior of the patient. Segmentation of scatter images is performed with two methods, thresholding and a deformable contour method. To achieve similarity of organ positions between scans, a positioning device is applied to the patient. Evaluation of the registration accuracy is performed with a) a I-131 phantom study, b) a Monte Carlo simulation study of an anthropomorphic phantom, and c) a I-123 patient trial. For a) r.m.s. distances between positions that should be equal in CT and SPECT are obtained to 1.0+/-0.7 mm, which thus for a rigid object is at sub pixel level. From b) results show that r.m.s. distances depend on the slice activity distribution. With a symmetrical distribution deviations are in the order of 5 mm. In c) distances between markers on the patient boundary an at the maximum 16 mm and on an average 10 mm. It is concluded that by utilizing the available Compton scatter data, valuable positioning information is achieved. that can be used for registration of SPECT images.

Abstract:   In this work Cellular Neural Networks are applied to image analysis techniques as a deformable models. To this end the problem is considered based on a discrete-time CNN with cyclic templates and time-variant external inputs. The appropriateness for a VLSI implementation and massively parallel computing of CNNs will permit a considerable improvement in processing speed with respect to the clasical active contours approaches.

Abstract:   Intravascular ultrasound (IVUS) imaging enables detailed analysis and precise measurements of vascular cross-sections. However, to achieve a reduction in the existing level of observer variability requires the development of quantitative IVUS. We have developed a fully automatic intraluminal edge detection technique, based on adaptive active contour models and called ADDER (adaptive damping dependent on echographic regions) that allows the quantitation of the intraluminal cross-sectional area (ICSA). Using a 30-MHz mechanically rotated transducer mounted at the tip of a 3.5-F catheter, 58 normal and pathologic arterial segments (from coronary, renal, splenic, iliac, and carotid arteries) were imaged in vitro. These images were analyzed by 2 experts, E1 and E2, who manually traced the intraluminal contour twice for each image, as well as with ADDER. Intra-observer variabilities for ICSAs were found to be excellent (-1.454+/-3.51% for E1, 0.96+/-5.4% for E2). The inter-observer variability was 2.1+/-4.3%. The success factor for ADDER was 89%. Its intra-observer variability was null, as the method always finds a unique contour. The correlation between the automatically detected ICSA and the manual ICSA was: r=0.99 (y=1.03x+0.89 mm(2)). Morphometric variations between manually and automatically traced contours, analyzed by the centerline method, were 100+/-140 mm on average. In conclusion, the ADDER automatic contour detection applied to IVUS images is robust and characterized by small systematic and random errors; therefore, quantitative IVUS is a useful tool in clinical research trials.

Abstract:   We present a novel geometric approach for solving the stereo problem for an arbitrary number of images (greater than or equal to 2). It is based upon the definition of a variational principle that must be satisfied by the surfaces of the objects in the scene and their images, The Euler-Lagrange equations that are deduced from the variational principle provide a set of partial differential equations (PDE's) that are used to deform an initial set of surfaces which then move toward the objects to he detected, The level set implementation of these PDE's potentially provides an efficient and robust way of achieving the surface evolution and to deal automatically with changes in the surface topology during the deformations, i.e., to deal with multiple objects, Results of an implementation of our theory also dealing with occlusion and vilility are presented on sydnthetic and real images.+

Abstract:   We propose a method for the 3D segmentation and representation of cortical folds with a special emphasis on the cortical sulci. These cortical structures are represented using "active ribbons". Active ribbons are built from active surfaces, which represent the median surface of a particular sulcus filled by CSF. Sulci modeling is obtained from MRI acquisitions (usually T1 images). The segmentation is performed using an automatic labeling procedure to separate gyri from sulci based on curvature analysis of the different iso-intensity surfaces of the original MRI volume. The outer parts of the sulci are used to initialize the convergence of the active ribbon from the outer parts of the brain to the interior. This procedure has two advantages: first, it permits the labeling of voxels belonging to sulci on the external part of the brain as well as on the inside (which is often the hardest point) and secondly, this segmentation allows 3D visualization of the sulci in the MRI volumetric environment as well as showing the sophisticated shapes of the cortical structures by means of isolated surfaces. Active ribbons can be used to study the complicated shape of the cortical anatomy, to model the variability of these structures in shape and position, to assist nonlinear registrations of human brains by locally controlling the warping procedure, to map brain neurophysiological functions into morphology or even to select the trajectory of an intra-sulci (virtual) endoscope.

Abstract:   The paper presents a knowledge-based method for automatic road extraction from aerial photography and high-resolution remotely sensed images. The method is based on Marr's theory of vision, which consists of low-level image processing for edge detection and linking, mid-level processing for the formation of road structure, and high-level processing for the recognition of roads. It uses a combined control strategy in which hypotheses are generated in a bottom-up mode and a top-down process is applied to predict the missing road segments. To describe road structures a generalized antiparallel pair is proposed. The hypotheses of road segments are generated based on the knowledge of their geometric and radiometric properties, which are expressed as rules in Prolog. They are verified using part-whole relationships between roads in high-resolution images and roads in low-resolution images and spatial relationships between verified road segments. Some results are presented in this paper. (C) 1998 Academic Press.

Abstract:   Reconstruction of the human cerebral cortex from MR images is a fundamental step in human brain mapping and in applications such as surgical path planning. In a previous paper, we described a method for obtaining a surface representation of the central layer of the human cerebral cortex using fuzzy segmentation and a deformable surface model. This method, however, suffers from several problems. In this paper, we significantly improve upon the previous method by using a fuzzy segmentation algorithm robust to intensity inhomogeneities, and using a deformable surface model specifically designed for capturing convoluted sulci or gyri. We demonstrate the improvement over the previous method both qualitatively and quantitatively, and show the result of its application to six subjects. We also experimentally validate the convergence of the deformable surface initialization algorithm.

Abstract:   In this paper we describe a new approach for 2-D object segmentation using an automatic method applied on images with problems as partial information, overlapping objects, many objects in a single scene, severe noise conditions and locating objects with a very high degree of deformation. We use a physically-based shape model to obtain a deformable template, which is defined on a canonical orthogonal coordinate system. The proposed methodology works starting from the output of an edge detector, which is processed to automatically obtain an approximation of the shape. The final estimation of the shapes is obtained fitting a deformable template model, which is defined on a learned surface of deformation. Results from biological images are presented. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Abstract:   In multidimensional image analysis, there are, and will continue to be, situations wherein automatic image segmentation methods fail, calling for considerable user assistance in the process. The main goals of segmentation research for such situations ought to be (i) to provide effective control to the user on the segmentation process while it is being executed, and (ii) to minimize the total user's time required in the process. With these goals in mind, we present in this paper two paradigms, referred to as live wire and live lane, for practical image segmentation in large applications. For both approaches, we think of the pixel vertices and oriented edges as forming a graph, assign a set of features to each oriented edge to characterize its "boundariness," and transform feature values to costs. We provide training facilities and automatic optimal feature and transform selection methods so that these assignments can be made with consistent effectiveness in any application. In live wire, the user first selects an initial point on the boundary. For any subsequent point indicated by the cursor, an optimal path from the initial point to the current point is found and displayed in real time. The user thus has a live wire on hand which is moved by moving the cursor, If the cursor goes close to the boundary, the live wire snaps onto the boundary. At this point, if the live wire describes the boundary appropriately, the user deposits the cursor which now becomes the new starting point and the process continues. A few points (live-wire segments) are usually adequate to segment the whole 2D boundary. in live lane, the user selects only the initial point. Subsequent points are selected automatically as the cursor is moved within a lane surrounding the boundary whose width changes as a function of the speed and acceleration of cursor motion. Live-wire segments are generated and displayed in real time between successive points. The users get the feeling that the curve snaps onto the boundary as and while they roughly mark in the vicinity of the boundary. We describe formal evaluation studies to compare the utility of the new methods with that of manual tracing based on speed and repeatability of tracing and on data taken from a large ongoing application. The studies indicate that the new methods are statistically significantly more repeatable and 1.5-2.5 times faster than manual tracing. (C) 1998 Academic Press.

Abstract:   In many computer vision and image understanding problems, it is important to find a smooth surface that fits a set of given unstructured 3D data. Although approaches based on general deformable models give satisfactory results, in particular a local description of the surface, they involve large linear systems to solve when dealing with high resolution 3D images. The advantage of parametric deformable templates like superquadrics is their small number of parameters to describe a shape. However, the set of shapes described by superquadrics is too limited to approximate precisely complex surfaces. This is why hybrid models have been introduced to refine the initial approximation. This article introduces a deformable superquadric model based on a superquadric fit followed by a free-form deformation (FFD) to fit unstructured 3D points. At the expense of a reasonable number of additional parameters, free-form deformations provide a much closer fit and a volumetric deformation field. We first present the mathematical and algorithmic details of the method. Then, since we are mainly concerned with applications for medical images, we present a medical application consisting in the reconstruction of the left ventricle of the heart from a number of various 3D cardiac images. The extension of the method to track anatomical structures in spatio-temporal images (4D data) is presented in a companion article [9]. (C) 1998 Academic Press.

Abstract:   In this paper we consider the problems encountered when applying snake models to detect the contours of the carpal bones in 3-D MR images of the wrist, In order to improve the performance of the original snake model introduced by Kass [1], we propose a new image force based on one-dimensional (1-D) second-order Gaussian filtering and contrast equalization, The improved snake is less sensitive to model initialization and has no tendency to cut off contour sections of high curvature, because 1-D radial scale-space relaxation is used, Contour orientation is used to minimize the influence of neighboring image structures. Due to 1-D contrast equalization an intensity insensitive measure of external energy is obtained. As a consequence a good balance between internal and external energetic contributions of the snake is established, which also improves convergence. By incorporating this new image force into the snake model, we succeed in accurate contour detection, even when relatively high noise levels are present and when the contrast varies along the contours of the bones.

Abstract:   In this paper, we propose an analytic-to-holistic approach which can identify faces at different perspective variations. The database for the test consists of 40 frontal-view faces. The first step is to locate 15 feature points on a face. A head model is proposed, and the rotation of the face can be estimated using geometrical measurements. The positions of the feature points are adjusted so that their corresponding positions for the frontal view are approximated. These feature points are then compared with the feature points of the faces in a database using a similarity transform. In the second step, we set up windows for the eyes, nose, and mouth. These feature windows are compared with those in the database by correlation. Results show that this approach can achieve a similar level of performance from different viewing directions of a face. Under different perspective variations, the overall recognition rates are over 84 percent and 96 percent for the first and the first three likely matched faces, respectively.

Abstract:   We describe an automatic storm-tracking system to help with the forecasting of severe storms. in this article, we present the concepts of fuzzy point, fuzzy vector, fuzzy length of a fuzzy vector, and fuzzy angle between two nonzero fuzzy vectors, that are used in our tracking algorithm. These concepts are used to overcome some of the limitations of our previous work, where fixed center-of-mass storm centers did not provide smooth tracks over time, while at the same time, their detection was very threshold sensitive. Our algorithm uses region splitting with dynamic thresholding to determine storm masses in Doppler radar intensity images. We represent the center of a hypothesized storm using a fuzzy point. These fuzzy storm centers are then tracked over time using an incremental relaxation algorithm. We have developed a visualization program using the X11 Athena toolkit for our storm visualization tool. The algorithm was tested on seven real radar image sequences obtained from the Atmospheric Environment Service radar station at King City, Ontario, Canada. We can obtain storm tracks that are long and smooth and which closely match an expert meteorologist's perception. (C) 1998 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 9, 201-213, 1998.

Abstract:   This paper studies mathematical methods in the emerging new discipline of Computational Anatomy. Herein we formalize the Brown/Washington University model of anatomy following the global pattern theory introduced in [1, 2], in which anatomies are represented as deformable templates, collections of 0, 1, 2, 3-dimensional manifolds. Typical structure is carried by the template with the variabilities accommodated via the application of random transformations to the background manifolds. The anatomical model is a quadruple (Omega, H, I, P), the background space Omega = boolean ORalpha M-alpha of 0, 1, 2, 3-dimensional manifolds, the set of diffeomorphic transformations on the background space H : Omega <-> Omega, the space of idealized medical imagery I, and P the family of probability measures on H. The group of diffeomorphic transformations H is chosen to be rich enough so that a large family of shapes may be generated with the topologies of the template maintained. For normal anatomy one deformable template is studied, with (Omega, H, I) corresponding to a homogeneous space [3], in that it can be completely generated from one of its elements, I = HItemp,I-temp is an element of I. For disease, a family of templates boolean ORalphaItempalpha are introduced of perhaps varying dimensional transformation classes. The complete anatomy is a collection of homogeneous spaces I-total = boolean ORalpha(I-alpha,H-alpha). There are three principal components to computational anatomy studied herein. (1) Computation of large deformation maps: Given any two elements I, I' is an element of I in the same homogeneous anatomy (Omega, H, I), compute diffeomorphisms h from one anatomy to the other I (h-1)reversible arrow(h) I'. This is the principal method by which anatomical structures are understood, transferring the emphasis from the images I is an element of I to the structural transformations h is an element of H that generate them. (2) Computation of empirical probability laws: Given populations of anatomical imagery and diffeomorphisms between them I h(n-1)reversible arrow(hn) I-n, n = 1, . . . , N, generate probability laws P is an element of P on H that represent the anatomical variation reflected by the observed population of diffeomorphisms h(n), n = 1,..., N. (3) Inference and disease testing: Within the anatomy (Omega, H, I, P), perform Bayesian classification and testing for disease and anomaly.

Abstract:   Magnetic resonance angiography (MRA) offers a non-invasive approach to the acquisition of anatomically accurate human arterial structure. Combining the latest computational fluid dynamics (CFD) techniques with clinical data from MRA, the detailed haemodynamics information in the human circulation system can be obtained. In this paper, a novel computer method is presented, which generates automatically a computational grid for a human abdominal bifurcation from a set of conventional MRA images. The method covers the complete sequence from MR image segmentation, 3-D model construction, grid generation, to grid quality evaluation. Results demonstrate that the computer program developed is capable of generating a good quality grid for human arterial bifurcations from MRA images with minimum user. input. The resultant grid can be used directly for further computer simulation of the flow. (C) 1998 Elsevier Science Ireland Ltd. All rights reserved.

Abstract:   Classification of farm animal behavior is based on oral or written descriptions of the activity in which the animal is engaged. The quantification of animal behavior for research requires that individuals recognize and code the behavior of the animal under study. The classification of these behaviors can be subjective and may differ among observers. Illustrated guides to animal behavior do not convey the motion associated with most behaviors. Video-based guides offer a method of quantifying behaviors with real-time demonstrations of the components that make up a behavior. An animal behavior encyclopedia has been developed to allow searching and viewing of defined (video-recorded) behaviors on the Internet. This video data base is being developed to initiate a system that automatically extracts animal motion information from an input animal activity video clip using a multiobject tracking and reasoning system. Eventually, the extracted information will be analyzed and described using standard animal behavior definitions (the behavior encyclopedia). The intended applications of the behavior encyclopedia and video tracking system are 1) an accessible data base for defining and illustrating behaviors for both research and teaching and 2) to further automate the collection of animal behavior data.

Abstract:   Reliable and efficient vessel cross-sectional boundary extraction is very important for many medical magnetic resonance (MR) image studies. General purpose edge detection algorithms often fail for medical MR images processing due to fuzzy boundaries, inconsistent image contrast, missing edge features, and the complicated background of MR images. In this regard, we present a vessel cross-sectional boundary extraction algorithm based on a global and local deformable model with variable stiffness. With the global model, the algorithm can handle relatively large vessel position shifts and size changes. The local deformation with variable stiffness parameters enable the model to stay right on edge points at the location where edge features are strong and at the same time, fit a smooth contour at the location where edge features are missing, Directional gradient information is used to help the model to pick correct edge segments. The algorithm was used to process MR cine phase-contrast images of the aorta from 20 volunteers (over 500 images) with excellent results. (C) 1998 Elsevier Science Inc.

Abstract:   Image morphing has received much attention in recent years. It has proven to be a powerful tool for visual effects in film and television, enabling the fluid transformation of one digital image into another. This paper surveys the growth of this field and describes recent advances in image morphing in terms of feature specification, warp generation methods, and transition control. These areas relate to the ease of use and quality of results. We describe the role of radial basis functions, thin plate splines, energy minimization, and multilevel free-form deformations in advancing the state-of-the-art in image morphing. Recent work on a generalized framework for morphing among multiple images is described.

Abstract:   We present an algorithm for morphing two images, often with little or no user interaction. For two similar images (such as different faces against a neutral background), the algorithm generally can create a pleasing morph completely automatically. The algorithm seeks to minimize the work needed to deform one image into the other. Work is defined as a function of the amount of warping and recoloration. We invoke a hierarchical method for finding a minimal work solution. Anchor point constraints are satisfied by penalties imposed on deformations that disobey these constraints. Good results can be obtained in less than 10 s for 256x256 images.

Abstract:   Dental CAD/CAM offers the prospects of drastically reducing the time to provide service to patients, with no compromise on quality. Given the state-of-the-art in sensing, design, and machining, an attractive approach is to have a technician generate a restorative design in wax, which can then be milled by a machine in porcelain or titanium. The difficulty stems from the inherent outlier noise in the measurement phase. Traditional techniques remove noise at the cost of smoothing, degrading discontinuities such as anatomical lines which require accuracy up to 5 to 10 mu m to avoid artifacts. This paper presents an efficient method for the automatic and accurate data validation and 3-D shape inference from noisy digital dental measurements. The input consists of 3-D points with spurious samples, as obtained from a variety of sources such as a laser scanner or a stylus probe. The system produces faithful smooth surface approximations while preserving critical curve features such as grooves and preparation lines. To this end, we introduce the Tensor Voting technique, which efficiently ignores noise, infers smooth structures, and preserves underlying discontinuities. This method is non-iterative, does not require initial guess, and degrades gracefully with spurious noise, missing and erroneous data. We show results on real and complex data.

Abstract:   Providing content-based video query, retrieval and browsing is the most important goal of a video database management system (VDBRIS). Video data is unique not only in terms of its spatial and temporal characteristics, but also in the semantic associations manifested by the entities present in the video. This paper introduces a novel video data model called Logical Hypervideo Data,Model. In addition to multilevel video abstractions, the model is capable of representing video entities that users are interested in (defined as hot objects) and their semantic associations with other logical video abstractions, including hot objects themselves. The semantic associations are modeled as video hyperlinks and video data with such property are called hypervideo. Video hyperlinks provide a flexible and effective way of browsing video data. Based on the proposed model, video queries can be specified with both temporal and spatial constraints, as well as with semantic descriptions of the video data. The characteristics of hot objects' spatial and temporal relations and efficient evaluation of them are also discussed. Some query examples are given to demonstrate the expressiveness of the video data model and query language. Finally, we describe a modular video database system architecture that our web-based prototype is based on.

Abstract:   Automatic computer processing of large multi-dimensional images such as those produced by magnetic resonance imaging (MRI) is greatly aided by deformable models. A general method of deforming polyhedra is presented here, with two novel features. Firstly, explicit prevention of non-simple (self-intersecting) surface geometries is provided, unlike conventional deformable models which merely discourage such behaviour. Secondly, simultaneous deformation of multiple surfaces with inter-surface proximity constraints provides a greater facility for incorporating model-based constraints into the process of image recognition. These two features are used advantageously to automatically identify the total surface of the cerebral cortical gray matter from normal human MR images, accurately locating the depths of the sulci even where under-sampling in the image obscures the visibility of sulci. A large number of individual surfaces (N=151) are created and a spatial map of the mean and standard deviation of the cerebral cortex and the thickness of cortical gray matter are generated. Ideas for further work are outlined.

Abstract:   A method is presented which aids the clinician in obtaining quantitative measurements of an abdominal aortic aneurysm from a CTA volume. These measurements are needed in the preoperative evaluation of candidates for minimally invasive aneurysmal repair. The user initializes starting points in the iliac artery, Subsequently, an iterative tracking procedure outlines the central lumen line in the aorta and the iliac arteries. Quantitative measurements on vessel morphology are performed in the planes perpendicular to the vessel axis. The entire process is performed in less than one minute on a standard workstation. In addition to the presentation of the calculated measures, a 3D view of the vessels is generated. This allows for interactive inspection of the vasculature and the tortuosity of the vessels.

Abstract:   In the present research a parallel algorithm for medical image processing has been proposed, which allows 3D quantitative analysis of left ventricular cardiac wall motion in real time. It is a fundamental task in evaluating a lot of indexes useful to perform diagnosis of important diseases. However, such analysis involves expensive tasks in terms of computational time: tridimensional segmentation and an accurate cavity contour detection during the entire cardiac cycle. In this paper an implementation of a dynamic quantitative analysis algorithm on low-cost Shared Memory Processor machine is described. In order to test the developed system in actual environment, a dynamic sequence of 3D data volume, derived from Magnetic Resonance (MR) cardiac images, has been processed.

Abstract:   A new method to segment MR volumes has been developed. The method matches elastically a 3D deformable prior model, describing the structures of interest, to the MR volume of a patient. The deformation is done using a deformation grid. Oriented distance maps are utilized to guide the deformation process. Two alternative restrictions are used to preserve the geometrical prior knowledge of the model. The method is applied to extract the body, the lungs and the heart. The segmentation is needed to build individualized boundary element models for bioelectromagnetic inverse problem. The method is fast, automatic and accurate. Good results have been achieved for four MR volumes tested so far.

Abstract:   This paper presents a method for automatic segmentation of the tibia and femur in clinical magnetic resonance images of knees. Texture information is incorporated into an active contours framework through the use of vector-valued geodesic snakes with local variance as a second value at each pixel, in addition to intensity. This additional information enables the system to better handle noise and the non-uniform intensities found within the structures to be segmented. It currently operates independently on 2D images (slices of a volumetric image) where the initial contour must be within the structure but not necessarily near the boundary. These separate segmentations are stacked to display the performance on the entire 3D structure.

Abstract:   The in vivo investigation of joint kinematics in normal and injured wrist requires the segmentation of carpal bones from 3D (CT) images and their registration over time. The non-uniformity of bone tissue, ranging from dense cortical bone to textured spongy bone, the irregular, small shape of closely packed carpel bones which move with respect to one another, and with respect to CT resolution, augmented with the presence of blood vessels, and the inherent blurring of CT imaging renders the segmentation of carpal bones a challenging task. Specifically, four characteristic difficulties are prominent: (i) gaps or weak edges in the carpal bone surfaces. (ii) diffused edges, (iii) textured regions, and, (iv) extremely narrow inter-bone regions. We review the performance of statistical classification! deformable models, region growing, and morphological operations for this application. We then propose a model which. combines several of these approaches in a single framework. Specifically, initialized seeds grow in a curve evolution implementation of active contours, but where growth is modulated by a skeletally-mediated competition between neighboring regions, thus combining the advantages of local and global region growing methods, region competition and active contours. This approach effectively deals with many of the difficulties presented above as illustrated by numerous examples.

Abstract:   We propose a new way of embedding shape distributions in a topological deformable template. These distributions rely on global shape descriptors corresponding to the 3D moment invariants. In opposition to usual Fourier-like descriptors, they can be updated during deformations at a relatively low cost. The moment-based distributions are included in a framework allowing the management of several simultaneously deforming objects. This framework is dedicated to the segmentation of brain deep nuclei in 3D MR images. The paper focuses on the learning of the shape distributions, on the initialization of the topological model and on the multi-resolution energy minimization process. Results are presented showing the segmentation of twelve brain deep structures.

Abstract:   Active contours, or snakes, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. A new type of external force for active contours, called gi adient vector flow (GVF) was introduced recently to address problems associated with initialization and poor convergence to boundary concavities. GVF is computed as a diffusion of the gradient vectors of a gray-level or binary edge map derived from the image. In this paper, we generalize the GVF formulation to include two spatially varying weighting functions. This improves active contour convergence to long, thin boundary indentations, while maintaining other desirable properties of GVF, such as an extended capture range. The original GVF is a special case of this new generalized GVF (GGVF) model. An error analysis for active contour results on simulated test images is also presented. (C) 1998 Elsevier Science B.V. All rights reserved.

Abstract:   To achieve geometric reconstruction from 3D datasets two complementary approaches have been widely used. On one hand, the deformable model framework locally applies forces to fit the data. On the other hand, the non-rigid registration framework computes a global transformation minimizing the distance between a template and the data. We first show that applying a global transformation on a surface template, is equivalent to applying certain global forces on a deformable model. Second, we propose a scheme which combines the registration and free-form deformation. This globally constrained deformation scheme allows us to control the amount of deformation from the reference shape with a single parameter. Finally, we propose a general algorithm for performing model-based reconstruction in a robust and accurate manner. Examples on both range data and medical images are used to illustrate and validate the globally constrained deformation framework. (C) 1998 Elsevier Science B.V. All rights reserved.

Abstract:   Automatic signature verification is a well-established and active research area with numerous applications. In contrast, automatic signature identification has been given little attention, although there is a vast array of potential applications that could use the signature as an identification tool. This paper presents a novel approach to the problem of signature identification. We introduce the use of the revolving active deformable model as a powerful way of capturing the unique characteristics of the overall structure of a signature. Experimental evidence as well as intuition support the idea that the overall structure of a signature uniquely determines the signature in the majority of cases. Our revolving active deformable model originates from the snakes introduced in computer vision by Kass et al., but its implementation has been tailored to the task at hand. This computer-generated model interacts with the virtual gravity field created by the image gradient. Ideally, the uniqueness of this interaction mirrors the uniqueness of the signature's overall structure. The proposed method obviates the use of a computationally expensive segmentation approach and is parallelizable. The experiments performed with a signature database show that the proposed method is promising. (C) 1998 Elsevier Science B.V. All rights reserved.

Abstract:   Through intraoperative electrical stimulation mapping, it is possible to identify sites on the surface of the brain that are essential for language function. Interesting correlations have been found between the distribution of these sites and behavioral traits such as verbal IQ. In previous work, tools were developed for building a reconstruction of a patient's cortical surface and using it to recover coordinates of essential language sites. However, considerable expertise was required to produce good reconstructions. This paper describes an improved version of the mapping procedure, in which segmentation is driven by a 3-D shape model. The model-based approach provides more intuitive control over the system, allowing a trained user to complete a surface reconstruction and mapping in about two hours. This level of performance makes it feasible to gather language maps for a large number of patients, which hopefully will lead to significant new findings about language organization in the brain.

Abstract:   This article provides a brief tutorial-cum-overview of motion planning for "flexible" shapes. The article takes the point of view that motion planning for flexible shapes, in a broad sense, essentially amounts to motion planning for systems with many degrees of freedom (dofs), a well-studied problem in robotics. We start with the basics of motion planning including an introduction to some key concepts, survey a number of recent approaches to solve the motion planning for systems with many dofs, discuss the application of some of these approaches to motion planning for flexible shapes, and report, on some recent work in this area.

Abstract:   This paper presents an automatic multiple-scale algorithm for delineation of individual tree crowns in high spatial resolution infrared colour aerial images. The tree crown contours were identified as zero-crossings, with convex grey-level curvature, which were computed on the intensity image for each image scale. A modified centre of curvature was estimated for every edge segment pixel. For each segment, these centre points formed a swarm which was modelled as a primal sketch using an ellipse extended with the mean circle of curvature. The model described the region of the derived tree crown based on the edge segment at the current scale. The sketch was rescaled with a significance value and accumulated for a scale interval. In the accumulated sketch, a tree crown segment was grown, starting at local peaks, under the condition that it was inside the area of healthy vegetation in the aerial image and did not trespass into a neighbouring crown segment. The method was evaluated by comparison with manual delineation and with ground truth on 43 randomly selected sample plots. It was concluded that the performance of the method is almost equivalent to visual interpretation. On the average, seven out of ten tree crowns were the same. Furthermore, ground truth indicated a large number of hidden trees. The proposed technique could be used as a basic tool in forest surveys.

Abstract:   In this paper, we show that existing shaped-based active contour models are not affine-invariant and we addressed the problem by presenting an affine-invariant snake model (AI-snake) such that its energy function are defined in terms local and global affine-invariant features. The main characteristic of the AI-snake is that, during the process of object extraction, the pose of the model contour is dynamically adjusted such that it is in alignment with the current snake contour by solving the snake-prototype correspondence problem and determining the required affine transformation. In addition, we formulate the correspondence matching between the snake and the object prototype as an error minimization process between two feature vectors which capture both local and global deformation information. We show that the technique is robust against object deformations and complex scenes. (C) 1998 Elsevier Science B.V.

Abstract:   We propose a two-step algorithm for almost unsupervised detection of linear structures, in particular, main axes in road networks, as seen in synthetic aperture radar (SAR) images. The first step is local and is used to extract linear features from the speckle radar image, which are treated as road-segment candidates. We present two local line detectors as well as a method for fusing information from these detectors, In the second global step, we identify the real roads among the segment candidates by defining a Markov random field (MRF) on a set of segments, which introduces contextual knowledge about the shape of road objects, The influence of the parameters on the road detection is studied and results are presented for various real radar images.

Abstract:   We introduce a new paradigm, the differential invariant signature curve or manifold, for the invariant recognition of visual objects. A general theorem of E. Cartan implies that two curves are related by a group transformation if and only if their signature curves are identical. The important examples of the Euclidean and equi-affine groups are discussed in detail. Secondly, we show how a new approach to the numerical approximation of differential invariants, based on suitable combination of joint invariants of the underlying group action, allows one to numerically compute differential invariant signatures in a fully group-invariant manner. Applications to a variety of fundamental issues in vision, including detection of symmetries, visual tracking, and reconstruction of occlusions, are discussed.

Abstract:   We define distances between geometric curves by the square root of the minimal energy required to transform one curve into the other. The energy is formally defined from a left invariant Riemannian distance on an infinite dimensional group acting on the curves, which can be explicitly computed. The obtained distance boils down to a variational problem for which an optimal matching between the curves has to be computed. An analysis of the distance when the curves are polygonal leads to a numerical procedure for the solution of the variational problem, which can efficiently be implemented, as illustrated by experiments.

Abstract:   We propose an automated approach to modeling drainage channels-and, more generally, linear features that lie on the terrain-from multiple images. It produces models of the features and of the surrounding terrain that are accurate and consistent and requires only minimal human intervention. We take advantage of geometric constraints and photommetric knowledge. First, rivers flow downhill and lie at the bottom of valleys whose floors tend to be either V- or U-shaped. Second, the drainage pattern appears in gray-level images as a network of linear features that can be visually detected. Many approaches have explored individual facets of this problem. Ours unifies these elements in a common framework. We accurately model terrain and features as 3-dimensional objects from several information sources that may be in error and inconsistent with one another. This approach allows us to generate models that are faithful to sensor data, internally consistent and consistent with physical constraints. We have proposed generic models that have been applied to the specific task at hand. We show that the constraints can be expressed in a computationally effective way and, therefore, enforced while initializing the models and then fitting them to the data. Furthermore, these techniques are general enough to work on other features that are constrained by predictable forces.

Abstract:   An important challenge in industrial metrology is to provide rapid measurement of critical three-dimensional (3-D) internal object geometry for either inspecting high volume parts or controlling a machining process, Existing metrological techniques are typically too slow to meet this need or can not measure small features with high precision. In this paper, we present a new method that achieves fast, accurate, internal 3-D geometry measurement based on 3-D reconstruction from a few X-ray views of a part, Our approach utilizes an accurate camera model for the X-ray sensor, calibration using in situ ground truth and geometry-guided X-ray feature extraction to achieve this goal and has been fully implemented in a prototype 3-D measurement system, We describe a novel application of the system to CAD-based verification of drilled hole positioning. Experimental results are given to illustrate the precision of the system and 3-D measurement on real industrial parts.

Abstract:   We propose a technique to increase the robustness of a snake-based segmentation method originally introduced to track the shape of a target with random white Gaussian intensity upon a random white Gaussian background. Because these statistical conditions are not always fulfilled with optronic images, we describe two improvements that increase the field of application of this approach. We first show that regularized whitening preprocessing allows one to apply the original method successfully for a target with a correlated texture upon a correlated background. We then introduce a simple multiscale approach that increases the robustness of the segmentation against the initialization of the snake (i.e., the initial shape used for the segmentation). These results provide a robust and practical method for determination of the reference image for correlation techniques. (C) 1998 Optical Society of America.

Abstract:   The problem of edge detection is viewed as a hierarchy of detection problems where the geometric objects to be detected (e.g., edge points, curves, regions) have increasing complexity and spatial extent. An early stage of the proposed hierarchy consists in detecting the regular portions of the visible edges. The input to this stage is given by a graph whose vertices are tangent vectors representing local and uncertain information about the edges. A model relating the input vector graph to the curves to be detected is proposed. An algorithm with linear time complexity is described which solves the corresponding detection problem in a worst-case scenario. The stability of curve reconstruction in the presence of uncertain information and multiple responses to the same edge is analyzed and addressed explicitly by the proposed algorithm.

Abstract:   This paper presents an algorithm for the estimation of the motion of textured objects undergoing nonrigid deformations over a sequence of images. An active mesh model, which is a finite-element deformable membrane, is introduced in order to achieve efficient representation of global and local deformations, The mesh is constructed using an adaptive triangulation procedure that places more triangles over high detail areas. Through robust least squares techniques and modal analysis, efficient estimation of global object deformations is achieved, based on a set of sparse displacement measurements. A local warping procedure is then applied to minimize the intensity matching error between subsequent images, and thus estimate local deformations, Among the major contributions of this paper are novel techniques developed to acquire knowledge of the object dynamics and structure directly from the image sequence, even in the absence of prior intelligence regarding the scene, Specifically, a coarse-to-fine estimation scheme is first developed, which adapts the model to locally deforming features. Subsequently, principal components modal analysis is used to accumulate knowledge of the object dynamics. This knowledge is finally exploited to constrain the object deformation. The problem of tracking the model over time is addressed, and a novel motion-compensated prediction approach is proposed to facilitate this. A novel method for the determination of the dynamical principal axes of deformation is developed, The experimental results demonstrate the efficiency and robustness of the proposed scheme, which has many potential applications in the areas of image coding, image analysis, and computer graphics.

Abstract:   We discuss the detection of a connected shape in a noisy image. Two types of image are considered: in the first a degraded outline of the shape is visible, while in the second the data are a corrupted version of the shape itself. In the first type the shape is defined by a thin outline of pixels with records that are different from those at pixels inside and outside the shape, while in the second type the shape is defined by its edge and pixels inside and outside the shape have different records. Our motivation is the identification of cross-sectional head shapes in ultrasound images of human fetuses. We describe and discuss a new approach to detecting shapes in images of the first type that uses a specially designed filter function that iteratively identifies the outline pixels of the head. We then suggest a way based on the cascade algorithm introduced by Jubb and Jennison (1991) of improving and considerably increasing the speed of a method proposed by Storvik (1994) for detecting edges in images of the second type.

Abstract:   This paper presents a novel method of velocity field estimation for the points on moving contours in a 2-D image sequence. The method determines the corresponding point in a next image frame by considering the curvature change of a given point on the contour. In traditional methods, there are errors in optical flow estimation for the points which have low curvature variations since those methods compute solutions by approximating normal optical flow. The proposed method computes optical flow vectors of contour points minimizing the curvature changes. As a first step, snakes are used to locate smooth curves in 2-D imagery. Thereafter, the extracted curves are tracked continuously. Each point on a contour has a unique corresponding point on the contour in the next frame whenever the curvature distribution of the contour varies smoothly. The experimental results showed that the proposed method computes accurate optical flow vectors for various moving contours. (C) 1997 Pattern Recognition Society. Published by Elsevier Science Ltd.

Abstract:   Active contours are an attractive choice to extract the head boundary, for deployment within a face recognition or model-based coding scenario. However, conventional snake approaches can suffer difficulty in initialisation and parameterisation. A dual active contour configuration using dynamic programming has been developed to resolve these difficulties by using a global energy minimisation technique and a simplified parameterisation, to enable a global solution to be obtained. The merits of conventional gradient descent based snake (local) approaches, and search-based (global) approaches are discussed. In application to find head and face boundaries in front-view face images, the new technique employing dynamic programming is deployed to extract the inner face boundary, along with a conventional normal-driven contour to extract the outer (head) boundary. The extracted contours appear to offer sufficient discriminatory capability for inclusion within an automatic face recognition system.

Abstract:   In this paper, we review the recently published work on deformable models. We have chosen to concentrate on 2D deformable models and relate the energy minimization approaches to the Bayesian formulations. We categorize the various active contour systems according to the definition of the deformable model. We also present in detail one particular formulation for deformable templates which combines edge, texture, color and region information for the external energy and model deformations using wavelets, splines or Fourier descriptors. We explain how these models can be used for segmentation, image retrieval in a large database and object tracking in a video sequence. (C) 1998 Elsevier Science B.V. All rights reserved.

Abstract:   In this paper the theory of deformable templates as a vector cycle in 2D is described. The deformable template model originated in (Grenander, 1983) and was further investigated in (Grenander st al., 1991). A template vector distribution is induced by parameter distributions from transformation matrices applied to the vector cycle. An approximation in the parameter distribution is introduced. The main advantage by using the deformable template model is the ability to simulate a wide range of objects constrained by e.g. their biological variations, and thereby improve restoration, segmentation and classification tasks. For the segmentation the Metropolis algorithm and simulated annealing are used in a Bayesian scheme to obtain a maximum a posteriori estimator. Different energy functions are introduced and applied to different tasks in a case study. The energy functions are local mean, local gradient and probability measurement. The case study concerns estimation of meat percent in pork carcasses. Given two cross-sectional images - one at the front and one near the ham of the carcass - the areas of lean and fat and a muscle in the lean area are measured automatically by the deformable templates. (C) 1998 Elsevier Science B.V. All rights reserved.

Abstract:   An image segmentation method is proposed, which combines mathematical morphology tools and active contours in two stages. First, contours are coarsely approximated by means of morphological operators. Second, these initial contours evolve under the influence of geometric and grey-level information, owing to the model of active contours. The performance of the method is evaluated according to the noise and is compared to the watershed algorithm. Then an application is finally presented for biomedical images of tumour tissue. (C) 1998 Elsevier Science B.V. All rights reserved.

Abstract:   Tracking human lips in video is an important but notoriously difficult task. To accurately recover their motions in 3D from any head pose is an even more challenging task, though still necessary for natural interactions. Our approach is to build and train 3D models of lip motion to make up for the information we cannot always observe when tracking. We use physical models as a prior and combine them with statistical models, showing how the two can be smoothly and naturally integrated into a synthesis method and a MAP estimation framework for tracking. We have found that this approach allows us to accurately and robustly track and synthesize the 3D shape of the lips from arbitrary head poses in a 2D video stream. We demonstrate this with numerical results on reconstruction accuracy, examples of static fits, and audio-visual sequences. (C) 1998 Elsevier Science B.V. All rights reserved.

Abstract:   In this paper, we propose a new image metamorphosis algorithm which uses elastic body splines to generate warp functions for interpolating scattered data points. The spline is based on a partial differential equation proposed by Navier that describes the equilibrium displacement of an elastic body subjected to forces. The spline maps can be expressed as the linear combination of an affine transformation and a Navier spline. The proposed algorithm generates a smooth warp that reflects feature point correspondences. It is efficient in time complexity and smoothly interpolated morphed images with only a remarkably small number of specified feature points. The algorithm allows each feature point in the source image to be mapped to the corresponding feature point in the destination image. Once the images are warped to align the positions of features and their shapes, the in-between facial animation from two given facial images can be defined by cross dissolving the positions of correspondence features and their shapes and colors. We describe an efficient cross-dissolve algorithm for generating the in-between images. (C) 1998 Published by Elsevier Science B.V. All rights reserved.

Abstract:   Image segmentation remains one of the major challenges in image analysis, since image analysis tasks are often constrained by how web previous segmentation is accomplished. In particular, many existing image segmentation algorithms fail to provide satisfactory results when the boundaries of the desired objects are not clearly defined by the image-intensity information. In medical applications, skilled operators are usually employed to extract the desired regions that may be anatomically separate but statistically indistinguishable. Such manual processing is subject to operator errors and biases, is extremely time consuming, and has poor reproducibility. We propose a robust algorithm for the segmentation of three-dimensional (3-D) image data based on a novel combination of adaptive K-mean clustering and knowledge-based morphological operations. The proposed adaptive K-mean clustering algorithm is capable of segmenting the regions of smoothly varying intensity distributions. Spatial constraints are incorporated in the clustering algorithm through the modeling of the regions by Gibbs random fields, Knowledge-based morphological operations are then applied to the segmented regions to identify the desired regions according to the a priori anatomical knowledge of the region-of-interest. This proposed technique has been successfully applied to a sequence of cardiac CT volumetric images to generate the volumes of left ventricle chambers at 16 consecutive temporal frames. Our final segmentation results compare favorably with the results obtained using manual outlining. Extensions of this approach to other applications can be readily made when a priori knowledge of a given object is available.

Abstract:   In this paper a method for the objective assessment of burn scars is proposed. The quantitative measures developed in this research provide an objective way to calculate elastic properties of burn scars relative to the surrounding areas, The approach combines range data and the mechanics and motion dynamics of human tissues. Active contours are employed to locate regions of interest and to find displacements of feature points using automatically established correspondences, Changes in strain distribution over time are evaluated, Given images at two time instances and their corresponding features, the finite element method Is used to synthesize strain distributions of the underlying tissues, This results in a physically based framework for motion and strain analysis. Relative elasticity of the burn scar is then recovered using iterative descent search for the best nonlinear finite element model that approximates stretching behavior of the region containing the burn scar, The results from the skin elasticity experiments illustrate the ability to objectively detect differences in elasticity between normal and abnormal tissue, These estimated differences in elasticity are correlated against the subjective judgments of physicians that are presently the practice.

Abstract:   In this paper implicit representations of deformable models for medical image enhancement and segmentation are considered. The advantage of implicit models over classical explicit models is that their topology can he naturally adapted to objects in the scene, A geodesic formulation of implicit deformable models is especially attractive since it has the energy minimizing properties of classical models, The aim of this pager is twofold, First, a modification to the customary geodesic deformable model approach is introduced by considering all the level sets in the image as energy minimizing contours. This approach is used to segment multiple objects simultaneously and for enhancing and segmenting cardiac computed tomography (CT) and magnetic resonance images. Second, the approach is used to effectively compare implicit and explicit models for specific tasks. This shows the complementary character of implicit models since in case of poor contrast boundaries or gaps in boundaries e.g. due to partial volume effects, noise, or motion artifacts, they do not perform well, since the approach is completely data-driven.

Abstract:   Objective This article describes a preliminary work on virtual reality applied to liver surgery and discusses the repercussions of assisted surgical strategy and surgical simulation on tomorrow's surgery. Summary Background Data Liver surgery is considered difficult because of the complexity and variability of the organ. Common generic tools for presurgical medical image visualization do not fulfill the requirements for the liver, restricting comprehension of a patient's specific liver anatomy. Methods Using data from the National Library of Medicine, a realistic three-dimensional image was created, including the envelope and the four internal arborescences. A computer interface was developed to manipulate the organ and to define surgical resection planes according to internal anatomy. The first step of surgical simulation was implemented, providing the organ with real-time deformation computation. Results The three-dimensional anatomy of the liver could be clearly visualized. The virtual organ could be manipulated and a resection defined depending on the anatomic relations between the arborescences, the tumor, and the external envelope. The resulting parts could also be visualized and manipulated. The simulation allowed the deformation of a liver model in real time by means of a realistic laparoscopic tool. Conclusions Three-dimensional visualization of the organ in relation to the pathology is of great help to appreciate the complex anatomy of the liver. Using virtual reality concepts (navigation, interaction, and immersion), surgical planning, training, and teaching for this complex surgical procedure may be possible. The ability to practice a given gesture repeatedly will revolutionize surgical training, and the combination of surgical planning and simulation will improve the efficiency of intervention, leading to optimal care delivery.

Abstract:   We are interested in descriptions of 3D data sets, as obtained from stereo or a 3D digitizer. We therefore consider as input a sparse set of points, possibly associated with certain orientation information. In this paper, we address the problem of inferring integrated high-level descriptions such as surfaces, So curves, and junctions from a sparse point set. While the method proposed by Guy and Medioni provides excellent results for smooth structures, it only detects surface orientation discontinuities but does not localize them. For precise localization, we propose a noniterative cooperative algorithm in which surfaces, curves, and junctions work together: Initial estimates are computed based on the work by Guy and Medioni, where each point in the given sparse and possibly noisy point set is convolved with a predefined vector mask to produce dense saliency maps. These maps serve as input to our novel extremal surface and curve algorithms for initial surface and curve extraction. These initial features are refined and integrated by using excitatory and inhibitory fields. Consequently, intersecting surfaces (resp. curves) are fused precisely at their intersection curves (resp. junctions). Results on several synthetic as well as real data sets are presented.

Abstract:   This paper presents a method that uses the level sets of volumes to reconstruct the shapes of 3D objects from range data. The strategy is to formulate 3D reconstruction as a statistical problem: find that surface which is mostly likely, given the data and some prior knowledge about the application domain. The resulting optimization problem is solved by an incremental process of deformation. We represent a deformable surface as the level set of a discretely sampled scalar function of three dimensions, i.e., a volume. Such level-set models have been shown to mimic conventional deformable surface models by encoding surface movements as changes in the greyscale values of the volume. The result is a voxel-based modeling technology that offers several advantages over conventional parametric models, including flexible topology, no need for reparameterization, concise descriptions of differential structure, and a natural scale space for hierarchical representations. This paper builds on previous work in both 3D reconstruction and level-set modeling. It presents a fundamental result in surface estimation from range data: an analytical characterization of the surface that maximizes the posterior probability. It also presents a novel computational technique for level-set modeling, called the sparse-field algorithm, which combines the advantages of a level-set approach with the computational efficiency and accuracy of a parametric representation. The sparse-field algorithm is more efficient than other approaches, and because it assigns the level set to a specific set of grid points, it positions the level-set model more accurately than the grid itself. These properties, computational efficiency and subcell accuracy, are essential when trying to reconstruct the shapes of 3D objects. Results are shown for the reconstruction objects from sets of noisy and overlapping range maps.

Abstract:   While the task of seamlessly merging computer-generated 3D objects into an image sequence can be done manually, such effort often lacks consistency across the images. It is also time consuming and prone to error. This paper proposes a framework that solves the occlusion problem without assuming a priori computer models from the input scene. It includes a new algorithm to derive approximate 3D models about the real scene based on recovered geometry information and user-supplied segmentation results. The framework has been implemented, and it works for amateur home videos. The result is an easy-to-use system for applications like the visualization of new architectures in a real environment.

Abstract:   Image segmentation is a fundamental problem in computer vision, for which deformable models offer a partial solution. Most deformable models work by performing some kind of edge detection; complementary region growing methods have not often been used. As a result, deformable models that track regions rather than edges have yet to be developed to a great extent. Active region models are a relatively new type of deformable model driven by a region energy that is a function of the statistical characteristics of an image. This paper describes the use of constrained active region models for frame-rate tracking in color video images on widely available computer hardware. Two of the many color representations now in use are reviewed for this purpose: the intensity-based RGB space and the more intuitive HSV space. Normalized RGB, which is essentially a measure of hue and saturation, emerges as the preferred representation because it is invariant to illumination changes and can be obtained from many frame-grabbers via a simple fast software transformation. Three types of motion are examined for constraining deformable models: rigid models can only translate and rotate to fit image features; conformal models can also change size; affine models exhibit two kinds of shearing in addition to the other components. Two methods are described for producing affine motion, given the desired unconstrained motion calculated by searching for local energy minima lying perpendicular to the model boundary. An existing method, based on iterative gradient descent, computes translating, rotating, scaling, and shearing forces which can be combined to produce affine and other types of motion. A faster, more accurate method uses least-squares minimization to approximate the desired motion; with this method it is also possible to derive specific equations for rigid and conformal motion and to correct for the aperture problem associated with the perpendicular search method. The advantages of the new least-squares method are illustrated by using it to drive an active region model via an affine transformation which tracks the movements of a robot arm at frame rate in color video images, (C) 1998 Academic Press.

Abstract:   Surgical simulation increasingly appears to be an essential aspect of tomorrow's surgery. The development of a hepatic surgery simulator is an advanced concept calling for a new writing system which will transform the medical world:virtual reality. Virtual reality extends the perception of ourfive senses by representing more than the real state of things by the means of computer sciences and robotics. it consists of three concepts. immersion, navigation and interaction, Three reasons have led us to develop this simulator: the first is to provide the surgeon with a comprehensive visualisation of the organ. The second reason is to allow for planning and surgical simulation that could be compared with the detailed flight-plan for a commercial let pilot. The third lies in the fact that virtual reality is an integrated part of the concept of computer assisted surgical procedure. The project consists bi a sophisticated simulator which has to includefive requirements, visual fidelity, interactivity, physical properties, physiological properties, sensory input and output. In this report we will describe how to get a realistic 3D model of the liver from bi-dimensional 2D medical images for anatomical and surgical training. The introduction of a tumor and the consequent planning and virtual resection is also described, as are force feedback and real-time interaction.

Abstract:   This paper describes a modelling method for continuous closed contours. The initial input data set consists of two-dimensional (2-D) points, which may be represented as a discrete function in a polar coordinate system. The method uses the Shannon interpolation between these data points to obtain the global continuous contour model. A minimal description of the contour is obtained using the link between the Shannon interpolation kernel and the Fourier series of polar development (FSPD) for periodic functions. The Shannon interpolation kernel allows the direct interpretation of the contour smoothness in terms of both samples and Fourier frequency domains. In order to deal with deformation point sources, often encountered in active modelling techniques, a method of local deformation is proposed. Each local deformation is performed in an angular sector centred on the deformation point source. All the neighbouring characteristic samples are displaced in order to minimize the oscillations of the newly created model outside the deformation sector. This deformation technique preserves the frequency characteristics of the contour, regardless of the number and the intensity of deformation sources. In this way, the technique induces a frequency modelling constraint, which may be subsequently used in an active detection and modelling environment. Experiments on synthetic and real data prove the efficiency of the proposed technique. The method is currently used to model contours of the left ventricle of the heart obtained from ultrasound apical images. This work is part of a larger project, the aim of which is to analyse the space and time deformations of the left ventricle. The 2-D Fourier-Shannon model is used as a basis for more complex three-dimensional and four-dimensional Fourier models, able to recover automatically the movement and deformation of the left ventricle of the heart during a cardiac cycle.

Abstract:   The active contour model, called snake, has been proved to be an effective method in contour detection. This method has been successfully employed in the areas of object recognition, computer vision, computer graphics and biomedical images. However, this model suffers from a great limitation, that is, it is difficult to locate concave parts of an object. In view of such a limitation, a segmented snake is designed and proposed in this paper. The basic idea of the proposed method is to convert the global optimization of a closed snake curve into local optimization on a number of open snake curves. The segmented snake algorithm consists of two steps. In the first step, the original snake model is adopted to locate the initial contour near the object boundary. In the second step, a recursive split-and-merge procedure is developed to determine the final object contour. The proposed method is able to locate all convex, concave and high curvature parts of an object accurately. A number of images are selected to evaluate the capability of the proposed algorithm and the results are encouraging. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Abstract:   We demonstrate the reconstruction of a 3D, time-varying bolus of radiotracer from first-pass data obtained by the dynamic SPECT imager, FASTSPECT, built by the University of Arizona. The object imaged is a CardioWest Total Artificial Heart. The bolus is entirely contained in one ventricle and its associated inlet and outlet tubes. The model for the radiotracer distribution is a time-varying closed surface parameterized by 162 vertices that are connected to make 960 triangles, with uniform intensity of radiotracer inside. The total curvature of the surface is minimized through the use of a weighted prior in the Bayesian framework. MAP estimates for the vertices, interior intensity and background count level are produced for diastolic and systolic frames, the only two frames analyzed. The strength of the prior is determined by finding the corner of the L-curve. The results indicate that qualitatively pleasing results are possible even with as few as 1780 counts per time frame (total after summing over all 24 detectors). Quantitative estimates of ejection fraction and wall motion should be possible if certain restrictions in the model are removed, e.g., the spatial homogeneity of the radiotracer intensity within the volume defined by the triangulated surface, and smoothness of the surface at the tube/ventricle join. (C) 1998 Optical Society of America.

Abstract:   In this paper we present a new 3D discrete dynamic surface model. The model consists of vertices and edges, which connect adjacent vertices. Basic geometry of the model surface is generated by triangle patches. The model deforms by internal and external forces. Internal forces are obtained from local geometry of the model and are related to the local curvature of the surface.;External forces, on the other hand, are based on the image data and are calculated from desired image features. We also present a method for generating an initial volume for the model from a stack of initial contours, drawn by the user on cross sections of the volumetric data. (C) 1998 Elsevier Science Ltd. All rights reserved.

Abstract:   The application of a discrete dynamic contour model for segmentation of the hippocampus from brain MRT has been investigated. Solutions to several common problems of dynamic contours in this case and similar cases have been developed. A new method for extracting the discontinuous boundary of a structure with multiple edges near the structure has been developed. The method is based on detecting and following edges by external forces. The reliability of the final contour and the model stability have been improved by using a continuous mapping of the external energy and limiting movements of the contour. The problem of optimizing the internal force weight has been overcome by making it dependent on the amount of the external force. Finally, the results of applying the proposed algorithm, which implements the above modifications, to multiple applications have been evaluated. (C) 1998 Elsevier Science Ltd. All rights reserved.

Abstract:   We present a new, interactive tool called Intelligent Scissors which we use for image segmentation. Fully automated segmentation is an unsolved problem, while manual tracing is inaccurate and laboriously unacceptable. However, Intelligent Scissors allow objects within digital images to be extracted quickly and accurately using simple gesture motions with a mouse. When the gestured mouse position comes in proximity to an object edge, a live-wire boundary "snaps" to, and wraps around the object of interest. Live-wire boundary detection formulates boundary detection as an optimal path search in a weighted graph. Optimal graph searching provides mathematically piece-wise optimal boundaries while greatly reducing sensitivity to local noise or other intervening structures. Robustness is further enhanced with on-the-fly training which causes the boundary to adhere to the specific type of edge currently being followed, rather than simply the strongest edge in the neighborhood. Boundary cooling automatically freezes unchanging segments and automates input of additional seed points. Cooling also allows the user to be much more free with the gesture path, thereby increasing the efficiency and finesse with which boundaries can be extracted. (C) 1998 Academic Press.

Abstract:   A number of active contour models have been proposed that unify the curve evolution framework with classical energy minimization techniques for segmentation, such as snakes, The essential idea is to evolve a curve (in two dimensions) or a surface (in three dimensions) under constraints from image forces so that it clings to features of interest in an intensity image, Recently, the evolution equation has been derived from first principles as the gradient dow that minimizes a modified length functional, tailored to features such as edges, However, because the how may be slow to converge in practice, a constant (hyperbolic) term is added to keep the curve/surface moving in the desired direction, In this paper, we derive a modification of this term based on the gradient how derived from a weighted area functional, with image dependent weighting factor, When combined with the earlier modified Length gradient dow, we obtain a partial differential equation (PDE) that offers a number of advantages, as illustrated by several examples of shape segmentation on medical images. In many cases the weighted area how may be used on its own, with significant computational savings.

Abstract:   In this work we present a new image segmentation strategy which operates by means of active contours implemented on a multilayer cellular neural network. The approach consists of an expanding and thinning process, guided by external information from a contour which evolves until it reaches the final desired position in the image processed. (C) 1998 Elsevier Science B.V. All rights reserved.

Abstract:   The cross-sectional area of different fiber types is an important anatomic feature in studying the structure and function of healthy and diseased human skeletal muscles. However, such studies are hampered by the thousands of fibers involved when manual segmentation has to be used. We have developed a semiautomatic segmentation method that uses computational geometry and recent computer vision techniques to significantly reduce the time required to accurately segment the fibers in a sample. The segmentation is achieved by simply pointing to the approximate centroid of each fiber. The set of centroids is then used to automatically construct the Voronoi polygons, which correspond to individual fibers. Each Voronoi polygon represents the initial shape of one active contour model, called a snake. In the energy minimization process, which is executed in several stages, different external forces and problem-specific knowledge are used to guide the snakes to converge to fiber boundaries. Our results indicate that this approach for segmenting muscle fiber images is fast, accurate, and reproducible compared with manual segmentation performed by experts. Cytometry 32:317-326, 1998. (C) 1998 Wiley-Liss, Inc.

Abstract:   Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify objects. The exact properties of human shape similarity judgements are not well understood yet, and this task is particularly difficult in domains where the shapes are not related by rigid transformations. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the contours of the shapes, through elastic matching. Special attention is devoted to objects that possess articulations, i.e. articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show that similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of importance, since although parts appear to play a significant role in visual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyhedral shapes with the same method. Finally, we describe shape similarity effects that cannot be handled by current approaches. (C) 1998 Elsevier Science Ltd. All rights reserved.

Abstract:   An automatic approach to road centerline reconstruction from stereo image sequences acquired by a mobile mapping system is introduced. The road centerline reconstruction is treated as an inverse problem and solved by global optimization techniques. The centerlines are described by a physical curve model, which is composed of an abstract material and deforms according to external and internal forces applied. The external forces, generated from the centerline information extracted from the image sequences, controls the local characteristics of the model. The internal forces, arising from a priori knowledge of the road shape, contribute to the global shape of the model. Unique constraints that exist only in mobile mapping image sequences are utilized. The developed system has been used for processing a large number of mobile mapping image sequences. Road centerlines of the images under different conditions have been reconstructed successfully. The research results also make a contribution to the general field of structure from motion and stereo.

Abstract:   We address the problem of adapting the functions controlling the material properties of 2-D snakes, and show how introducing oriented smoothness constraints results in a novel class of active contour models for segmentation, which extends standard isotropic inhomogeneous membrane/thin-plate stabilizers. These constraints, expressed as adaptive L-2 matrix norms, are defined by two second-order symmetric and positive definite tensors that are invariant with respect to rigid motions in the image plane. These tensors, equivalent to directional adaptive stretching and bending densities, are quadratic with respect to first- and second-order derivatives of the image luminance, respectively. A representation theorem specifying their canonical form is established and a geometrical interpretation of their effects is developed. Within this framework, it is shown that by achieving a directional control of regularization such nonisotropic constraints consistently relate the differential properties (metric and curvature) of the deformable model with those of the underlying luminance surface, yielding a satisfying preservation of image contour characteristics. In particular, this model adapts to nonstationary curvature variations along image contours to be segmented, thus providing a consistent solution to curvature underestimation problems encountered near high curvature contour points by classical snakes evolving with constant material parameters. Optimization of the model within continuous and discrete frameworks is discussed in detail. Finally, accuracy and robustness of the model are established on synthetic images. Its efficacy is further demonstrated on 2-D MRI sequences for which comparisons with segmentations obtained using classical snakes are provided. (C) 1998 SPIE and IS&T. [S1017-9909(98)02101-1].

Abstract:   A fundamental open problem in computer vision-determining pose and correspondence between two sets of points in space-is solved with a novel, fast, robust and easily implementable algorithm. The technique works on noisy 2D or 3D point sets that may be of unequal sizes and may differ by non-rigid transformations. Using a combination of optimization techniques such as deterministic annealing and the softassign, which have recently emerged out of the recurrent neural network/statistical physics framework, analog objective functions describing the problems are minimized. Over thirty thousand experiments, on randomly generated points sets with varying amounts of noise and missing and spurious points, and on hand-written character sets demonstrate the robustness of the algorithm. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Abstract:   Experimental observations suggest that contour integration may take place in V1. However, there has yet to be a model of contour integration that uses only known V1 elements, operations, and connection patterns. This article introduces such a model, using orientation selective cells, local cortical circuits, and horizontal intracortical connections. The model is composed of recurrently connected excitatory neurons and inhibitory interneurons, receiving visual input via oriented receptive fields resembling those found in primary visual cortex. Intracortical interactions modify initial activity patterns from input, selectively amplifying the activities of edges that form smooth contours in the image. The neural activities produced by such interactions are oscillatory and edge segments within a contour oscillate in synchrony. It is shown analytically and empirically that the extent of contour enhancement and neural synchrony increases with the smoothness, length, and closure of contours, as observed in experiments on some of these phenomena. In addition, the model incorporates a feedback mechanism that allows higher visual centers selectively to enhance or suppress sensitivities to given contours, effectively segmenting one from another. The model makes the testable prediction that the horizontal cortical connections are more likely to target excitatory (or inhibitory) cells when the two linked cells have their preferred orientation aligned with (or orthogonal to) their relative receptive field center displacements.

Abstract:   Image warping is a transformation which maps all positions in one image plane to positions in a second plane. It arises in many image analysis problems, whether in order to remove optical distortions introduced by a camera or a particular viewing perspective, to register art image with a map or template, or to align two or more images. The choice of warp is a compromise between a smooth distortion and one which achieves a good match. Smoothness can be ensured by assuming a parametric form for the warp or by constraining it using differential equations. Matching can be specified by points to be brought into alignment, by local measures of correlation between images, or by the coincidence of edges. Parametric and non-parametric approaches to warping, and matching criteria, are reviewed.

Abstract:   RATIONALE AND OBJECTIVES. The authors develop a three-dimensional (3-D) deformable surface model-based segmentation scheme for abdominal computed tomography (CT) image segmentation. METHODS. A parameterized 3-D surface model was developed to represent the human abdominal organs. An energy function defined on the direction of the image gradient and the surface normal of the deformable model was introduced to measure the match between the model and image data. A conjugate gradient algorithm was adapted to the minimization of the energy function. RESULTS. Test results for synthetic images showed that the incorporation of surface directional information improved the results over those using only the magnitude of the image gradient. The algorithm was tested on 21 CT datasets. Of the 21 cases tested, 11 were evaluated visually by a radiologist and the results were judged to be without noticeable error. The other 10 were evaluated over a distance function. The average distance was less than 1 voxel. CONCLUSIONS. The deformable model-based segmentation scheme produces robust and acceptable outputs on abdominal CT images.

Abstract:   Snakes, or active contours, are used extensively in computer vision and image processing applications, particularly to locate object boundaries, problems associated with initialization and poor convergence to boundary concavities, however, have limited their utility, This paper presents a new external force for active contours, largely solving both problems. This external forte, which we call gradient vector flow (GVF), is computed as a diffusion of the gradient vectors of a gray-level or binary edge map derived from the image. It differs fundamentally from traditional snake external forces in that it cannot be written as the negative gradient of a potential function, and the corresponding snake is formulated directly from a force balance condition rather than a variational formulation. Using several two-dimensional (2-D) examples and one three-dimensional (3-D) example, we show that GVF has a large capture range and is able to move snakes into boundary concavities.

Abstract:   In the past several years, the speed of standard processors has reached the point where interesting problems requiring visual tracking can be carried out on standard workstations. However, relatively little attention has been devoted to developing visual tracking technology in its own right. In this article, we describe X Vision, a modular, portable framework for visual tracking. X Vision is designed to be a programming environment for real-time vision which provides high performance on standard workstations outfitted with a simple digitizer. X Vision consists of a small set of image-level tracking primitives, and a framework for combining tracking primitives to form complex tracking systems. Efficiency and robustness are achieved by propagating geometric and temporal constraints to the feature detection level, where image warping and specialized image processing are combined to perform feature detection quickly and robustly. Over the past several years, we have used X Vision to construct several vision-based systems. We present some of these applications as an illustration of how useful, robust tracking systems can be constructed by simple combinations of a few basic primitives combined with the appropriate task-specific constraints. (C) 1998 Academic Press.

Abstract:   By following the general approach of deformable templates, the problem of recognizing a single word, independently of the speaker, is shown to lead to the computation of the minimum value of some particular functional. More precisely, this allows us to recover, for each possible word in a prespecified set, the best matching with the recorded signal; by selecting the minimum value, the recognition problem can be solved. In this paper we are concerned with the detailed study of the variational problem associated with this sort of functional, namely, the existence of a minimum point and the features of such a minimum. Finally, we discuss the convergence of a discretized finite-dimensional approximation, suggested by the engineering literature on this subject.

Abstract:   The lack of information about tangential velocity makes velocity estimation erroneous in contour matching. Classical methods use the normal velocity, together with some smoothness constraints, since the tangential velocity cannot be recovered. This paper presents a contour matching method that computes displacements with a criteria of minimum curvature differences. The first derivative of tangential velocity is available from the image intensities and is related to the contour curvature. We compute the velocities using the curvature as well as the normal component. Consequently, the estimation error due to the tangential component is reduced substantially. A contour having occluding parts leads to mismatching. Our method determines occluding parts before the contour matching by analyzing the change of curvature distribution. Experimental results showed that the proposed method computes accurate velocity vectors for various moving contours. (C) 1998 Elsevier Science B.V.

Abstract:   Reconstruction of objects from a scene may be viewed as a data fitting problem using energy minimizing splines as the basic shape. The process of obtaining the minimum to construct the "best" shape can sometimes be important. Some of the potential problems in the Euler-Lagrangian variational solution proposed in the original formulation [1], were brought to light in [2], and a dynamic programming (DP) method was also suggested. In this paper we further develop the DP solution. We show that in certain cases, the discrete form of the solution in [2], and adopted subsequently [3], [4], [5], [6] may also produce local minima, and develop a strategy to avoid this. We provide a stronger form of the conditions necessary to derive a solution when the energy depends on the second derivative, as in the case of "active contours.".

Abstract:   A method is developed for feature-based coding of human face images. Deformable templates, wavelet decomposition, and residual vector quantization (RVQ) form three consecutive stages of the proposed method, which aims for recognition-based very low bit rate coding. Deformable templates are employed in localization of facial features and biorthogonal spline filters are used for the decomposition of segmented and normalized face images. Wavelet coefficients are zonal truncated before being vector quantized to generate multiresolution codebooks. Classified multiresolution codebooks are also generated for residual eye and mouth images to improve subjective quality of salient face features. (C) 1998 Society of Photo-Optical Instrumentation Engineers. [S0091-3286(98)02105-9].

Abstract:   This paper presents a computerized method for automated detection of the boundary of the os calcis on in vivo ultrasound parametric images, using an active dynamic contour model. The initial contour, defined without user interaction, is an iso-contour extracted from the textural feature space. The contour is deformed through the action of internal and external forces, until stability is reached. The external forces, which characterize image features, are a combination of gray-level information and second-order textural features arising from local cooccurrence matrices. The broadband ultrasound attenuation (BUA) value is then averaged within the contour obtained. The method was applied to 381 clinical images. The contour was correctly detected in the great majority of the cases, For the short-term reproducibility study, the mean coefficient of variation was equal to 1.81% for BUA values and 4.95% for areas in the detected region. Women with osteoporosis had a lower BUA than age-matched controls (p = 0.0005). In healthy women, the age-related decline was -0.45 dB/MHz/yr. In the group of healthy post-menopausal women, years since menopause, weight and age were significant predictors of BUA, These results are comparable to those obtained when averaging BUA values in a small region of interest.

Abstract:   A robust fully automatic method for segmenting the brain from head magnetic resonance (MR) images has been developed, which works even in the presence of radio frequency (RF) inhomogeneities. It has been successful in segmenting the brain in every slice from head images acquired from several different MRI scanners, using different-resolution images and different echo sequences. The method uses an integrated approach which employs image processing techniques based on anisotropic filters and "snakes" contouring techniques, and a priori knowledge, which is used to remove the eyes, which are tricky to remove based on image intensity alone, It is a multistage process, involving first removal of the background noise leaving a head mask, then finding a rough outline of the brain, then refinement of the rough brain outline to a final mask. The paper describes the main features of the method, and gives results for some brain studies.

Abstract:   An image segmentation system was developed for detecting the muscle longissimus thoraces (LT) in ultrasonic images of live pigs. The images have a low contrast, a high level of noise, and a high degree of variance in terms of texture and shape. The segmentation algorithm starts with a region growing process, which provides a rough approximation of the LT. Morphological operations and curve fitting eliminate unwanted noise. Finally, an active contour process refines the shape of the resulting region. This system takes several segmentation techniques and builds a flow of information between them but does not rely on specific a priori information of the texture or the contrast. This is a first step towards automating the loin detection in ultrasonic images of live pigs. initial experiments provided encouraging results. It is a modular system so that different region growing and refinement algorithms can be easily substituted into the current design. This makes for a general system that can be adapted to other segmentation tasks involving low contrast images. A series of three ultrasound images was made along the dorsal surface of 30 live pigs. Using the images to estimate loin volume, 64 and 70% of the variation in commercial loin weight and lean yield of loin were predicted. Augmenting the model with backfat measurements, the R-2 increased to 79 and 89%, respectively. These values compare to 76 and 79%, respectively, from measurements made on the carcass with the Hennessey Grading Probe.

Abstract:   The first virtual humans appeared in the early 1980's in such films as Dreamflight (1982) and The Juggler (1982). Pioneering work in the ensuing period focused on realistic appearance in the simulation of virtual humans. In the 1990's, the emphasis has shifted to real-time animation and interaction in virtual worlds. Virtual humans halle begun to inhabit virtual worlds and so have we. To prepare our place in the virtual world, we first develop techniques for the automatic representation of a human face capable of being animated in real time using both video and audio input. The objective is for one's representative to look, talk, and behave like oneself in the virtual world. Furthermore, the virtual inhabitants of this world should be able to see our avatars and to react to what we say and to the emotions we convey. This paper sketches an overview of the problems related to the analysis and synthesis of face-to-virtual-face communication in a virtual world. We describe different components of our system for real-time interaction and communication between a cloned face representing a real person and an autonomous virtual face. It provides an insight into the various problems and gives particular solutions adopted in reconstructing a virtual clone capable of reproducing the shape and movements of the real person's face. It includes the analysis of the facial expression and speech of the cloned face, which can be used to elicit a response from the autonomous virtual human with both verbal and nonverbal facial movements synchronized with the audio voice. We believe that such a system can be exploited in many applications such as natural and intelligent human-machine interfaces, virtual collaboration work, virtual learning and teaching, and so on.

Abstract:   In this paper, we address the issue of recovering and segmenting the apparent velocity field in sequences of images. As for motion estimation, we minimize an objective function involving two robust terms. The first one cautiously captures the optical flow constraint, while the second (a priori) term incorporates a discontinuity-preserving smoothness constraint. To cope with the nonconvex minimization problem thus defined, we design an efficient deterministic multigrid procedure. It converges fast toward estimates of good quality, while revealing the large discontinuity structures of flow fields. We then propose an extension of the model by attaching to it a flexible object-based segmentation device based on deformable closed curves (different families of curve equipped with different kinds of prior can be easily supported). Experimental results on synthetic and natural sequences are presented, including an analysis of sensitivity to parameter tuning.

Abstract:   A local smoothing operator applied in the reverse direction is used to obtain planar shape enhancement and exaggeration. Inversion of a smoothing operator is an inherently unstable operation. Therefore, a stable numerical scheme simulating the inverse smoothing effect is introduced. Enhancement is obtained for short time spans of evolution. Carrying the evolution further yields shape exaggeration or caricaturization effect. Introducing attraction forces between the evolving shape and the initial one yields an enhancement process that converges to a steady state. These forces depend on the distance of the evolving curve from the original one and on local properties. Results of applying the unrestrained and restrained evolution on planar shapes, based on a stabilized inverse geometric heat equation, are presented showing enhancement and caricaturization effects. (C) 1998 Academic Press.

Abstract:   In this paper we propose a new general framework for the application of the nonlinear finite element method (FEM) to nonrigid motion analysis, We construct the models by integrating image data and prior knowledge, using well-established techniques from computer vision, structural mechanics, and computer-aided design (CAD). These techniques guide the process of optimization of mesh models. Linear FEM proved to be a successful physically based modeling tool in solving limited types of nonrigid motion problems, However, linear FEM cannot handle nonlinear materials or large deformations. Application of nonlinear FEM to nonrigid motion analysis has been restricted by difficulties with high computational complexity and noise sensitivity. We tackle the problems associated with nonlinear FEM by changing the parametric description of the object to allow easy automatic control of the model, using physically motivated analysis of the possible displacements to address the worst effects of the noise, applying mesh control strategies, and utilizing multiscale methods. The combination of these methods represents a new systematic approach to a class of nonrigid motion applications for which sufficiently precise and flexible FEM models can be built, The results from the skin elasticity experiments demonstrate the success of the proposed method. The model allows us to objectively detect the differences in elasticity between normal and abnormal skin, Our work, demonstrates the possibility of accurate computation of point correspondences and force recovery from range image sequences containing nonrigid objects and large motion. (C) 1998 Academic Press.

Abstract:   The snake model, that involves a recursive scheme for contour searching, is widely employed in object contour detection. In a recursive algorithm, a terminating criterion is essential to terminate the process. However, existing terminating criteria for snake cannot acquire good results for contour detection. Two commonly employed terminating criteria for snake are addressed and their limitations on stability and reliability are discussed. A novel terminating criterion, named as contour length criterion (CL-criterion), is developed and reported in this paper. This criterion measures the normalized total length of the contour at each iteration. A number of images are selected to evaluate the effect of applying the proposed terminating criterion on the snake model and the results are encouraging. Compared to existing criteria, the proposed method is more stable and reliable. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Abstract:   In this paper a new snake model for image morphing with semiautomated delineation which depends on Hermite's interpolation theory, is presented. The snake model will be used to specify the correspondence between features in two given images. It allows a user to extract a contour that defines a facial feature such as the lips, mouth, and profile, by only specifying the endpoints of the contour around the feature which we wish to define. We assume that the user can specify the endpoints of a curve around the features that serve as the extremities of a contour. The proposed method automatically computes the image information around these endpoints which provides the boundary conditions. Then the contour is optimized by taking this information into account near its extremities. During the iterative optimization process, the image forces are turned on progressively from the contour extremities toward the center to define the exact position of the feature. The proposed algorithm helps the user to easily define the exact position of a feature. It may also reduce the time required to establish the features of an image.

Abstract:   We present a new active contour model for boundary tracking and position prediction of nonrigid objects, which results from applying a velocity control to the class of elastodynamical contour models, known as snakes, The proposed control term minimizes an energy dissipation function which measures the difference between the contour velocity and the apparent velocity of the image. Treating the image video-sequence as continuous measurements along time, it is shown that the proposed control results in robust tracking. This is in contrast to the original snake model which is proven to have tracking errors relative to image (object) velocity, thus resulting in high sensitivity to image clutter. The motion estimation further allows for position prediction of nonrigid boundaries. Based on the proposed central approach, we propose a new class of real time tracking contours, varying from models with batch-mode control estimation to models with real time adaptive controllers. (C) 1999 Academic Press.

Abstract:   The problem of determining the camera motion from apparent contours or silhouettes of a priori unknown curved three-dimensional surfaces is considered. In a sequence of images, it is shown how to use the generalized epipolar constraint an apparent contours. One such constraint is obtained for each epipolar tangency point in each image pair. An accurate algorithm for computing the motion is presented based on a maximum likelihood estimate. It is shown how to generate initial estimates on the camera motion using only the tracked contours. It is also shown that in theory the motion can be calculated from the deformation of a single contour. The algorithm has been tested on several real image sequences, for both Euclidean and protective reconstruction. The resulting motion estimate is compared to motion estimates calculated independently using standard feature-based methods. The motion estimate is also used to classify the silhouettes as curves or apparent contours. This is a strong indication that the motion estimate is of good quality. The statistical evaluation shows that the technique gives accurate and stable results.

Abstract:   We introduce a methodology for the alignment of multidimensional data, such as brain scans. The proposed approach does not require fiducial-point correspondence; correspondence of surfaces provides sufficient data for registration. We extend multidimensional interpolation theory by using a more general form of energy functional, which leads to basis functions that have different orders at zero and infinity. This allows flexibility in the design of the interpolation solution. The problem is transformed into a linear algebra problem. Two techniques for better conditioning of the system matrix are described. Experimental results on two- and three-dimensional alignment of brain data used in neurochemistry research are shown. (C) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Abstract:   Magnetic resonance (MR) tagging has been Shown to, be a useful technique for noninvasively measuring the deformation of an in vivo heart. An important step in analyzing tagged images is the identification of tag lines in each image of a cine sequence. Most existing tag identification algorithms require user defined myocardial contours. Contour identification, however, is time consuming and requires a considerable amount of user intervention. In this paper, a new method for identifying tag lines, which me call the ML/MAP method, is presented that does not require user defined myocardial contours. The ML/MAP method is composed of three stages. First, a set of candidate tag line centers is estimated across the entire region-of-interest (ROI) with a snake algorithm based on a maximum-likelihood (ML) estimate of the tag center. Next, a maximum a posteriori (MAP) hypothesis test is used to detect the candidate tag centers that are actually part of a tag line. Finally, a pruning algorithm is used to remove any detected tag line centers that do not meet a spatio-temporal continuity criterion. The ML/MAP method is demonstrated on data from ten in vivo human hearts.

Abstract:   In this paper, we consider the problem of matching tno-dimensional (2-D) planar object curves from a database, and tracking moving object curves through an image sequence, The first part of the paper describes a curve data compression method using B-spline curve approximation. We present a new constrained active B-spline curie model based on the minimum mean square error (MMSE) criterion, and an iterative algorithm for selecting the "best" segment border points for each B-spline curve, The second part of the paper describes a method for simultaneous object tracking and affine parameter estimation using the approximate curves and profiles, We propose a novel B-spline point assignment algorithm which incorporates the significant corners for interpolating corresponding paints on the two curves to be compared. A gradient-based algorithm is presented for simultaneously tracking object curl es, and estimating the associated translation, rotation and scaling parameters. The performance of each proposed method is evaluated using still images and image sequences containing simple objects.

Abstract:   A discrete dynamic model for defining and tracking contours in 2-D medical images is presented. An active contour in this objective is optimized by a dynamic programming algorithm, for which a new constraint that has fast and stable properties is introduced. The internal energy of the model depends on local behavior of the contour, while the external energy is derived from image features. The algorithm is able to rapidly detect convex and concave objects even when the image quality is poor. (C) 1999 Elsevier Science B.V. All rights reserved.

Abstract:   This paper considers the problem of generating various calligraphy from some sample fonts. Our method is based on the deformable contour model g-snake. By representing the outline of each stroke of a character with a g-snake, we cast the generation problem into global and local deformation of g-snake under different control parameters, where the local deformation obeys the energy minimization principle of regularization technique. The base values of the control parameters are learned from given sample fonts. The experimental results on alphabet and Japanese characters Hiragana show such processing as a reasonable method for generating calligraphy.

Abstract:   This paper considers the problem of generating various calligraphy from some sample fonts. Our method is based on the deformable contour model g-snake. By representing the outline of each stroke of a character with a g-snake, we cast the generation problem into global and local deformation of g-snake under different control parameters, where the local deformation obeys the energy minimization principle of regularization technique. The base values of the control parameters are learned from given sample fonts. The experimental results on alphabet and Japanese characters Hiragana show such processing as a reasonable method for generating calligraphy.

Abstract:   This paper presents a model-based approach to locate head and face boundaries in a head-shoulder image with plain background. Three models are constructed for the images, where the head boundary is divided into left/right sub-boundaries and the face boundary is divided into left/right and top/bottom sub-boundaries. The left/right head boundaries are located from two thresholded images and the final result is the combination of them. After the head boundary is located, the four face sub-boundaries are located from the grey edge image. The algorithm is carried out iteratively by detecting low-level edges and then organizing/verifying them using high-level knowledge of the general shape of a head. The experimental results using a database of 300 images show that this approach is promising. (C) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Abstract:   An approach for the automatic extraction of roads from digital aerial imagery is proposed. It makes use of several versions of the same aerial image with different resolutions. Roads are modeled as a network of intersections and links between these intersections, and are found by a grouping process. The context of roads is hierarchically structured into a global and a local level. The automatic segmentation of the aerial image into different global contexts, i.e., rural, forest, and urban area, is used to focus the extraction to the most promising regions. For the actual extraction of the roads, edges are extracted in the original high resolution image (0.2 to 0.5 m) and lines are extracted in an image of reduced resolution. Using both resolution levels and explicit knowledge about roads, hypotheses for road segments are generated. They are grouped iteratively into larger segments. in addition to the grouping algorithms, knowledge about the local context, e.g., shadows cast by a tree onto a road segment, is used to bridge gaps. To construct the road network, finally intersections are extracted. Examples and results of an evaluation based on manually plotted reference data are given, indicating the potential of the approach.

Abstract:   A snake model for convex tracking contours in 2D medical images is presented. By modelling the local behaviour of the contour, a new constraint that has fast and stable properties is obtained with optimisation by a dynamic programming algorithm.

Abstract:   Idiopathic scoliosis is the most common spinal deformity, affecting perhaps as many as 5% of children. Early recognition of the condition is essential for optimal treatment. A widely used technique for identification is based on a somewhat crude angle measurement from a frontal spinal X-ray. Here, we provide a technique and new summary statistical measures for classifying spinal shape, and present results obtained from clinical X-rays.

Abstract:   Aim-To recognise automatically the main components of the fundus on digital colour images. Methods-The main features of a fundus retinal image were defined as the optic disc, fovea, and blood vessels. Methods are described for their automatic recognition and location. 112 retinal images were preprocessed via adaptive, local, contrast enhancement. The optic discs were located by identifying the area with the highest variation in intensity of adjacent pixels. Blood vessels were identified by means of a multilayer perceptron neural net, for which the inputs were derived from a principal component analysis (PCA) of the image and edge detection of the first component of PCA. The foveas were identified using matching correlation together with characteristics typical of a fovea-for example, darkest area in the neighbourhood of the optic disc. The main components of the image were identified by an experienced ophthalmologist for comparison with computerised methods. Results-The sensitivity and specificity of the recognition of each retinal main component was as follows: 99.1% and 99.1% for the optic disc; 83.3% and 91.0% for blood vessels; 80.4% and 99.1% for the fovea. Conclusions-In this study the optic disc, blood vessels, and fovea were accurately detected. The identification of the normal components of the retinal image will aid the future detection of diseases in these regions. In diabetic retinopathy, for example, an image could be analysed for retinopathy with reference to sight threatening complications such as disc neovascularisation, vascular changes, or foveal exudation.

Abstract:   A 3-D multicriterion automatic segmentation algorithm is developed to improve accuracy of delineation of pulmonary nodules on helical computed tomography (CT) images by removing their adjacent structures. The algorithm applies multiple gray-value thresholds to a nodule region of interest (ROI). At each threshold level, the nodule candidate in the ROI is automatically detected by labeling 3-D connected components, followed by a 3-D morphologic opening operation. Once the nodule candidate is found, its two specific parameters, gradient strength of the nodule surface and a 3-D shape compactness factor, can be computed. The optimal threshold can be determined by analyzing these parameters. Our experiments with in vivo nodules demonstrate the feasibility of employing this algorithm to improve the accuracy of nodule delineation, especially for small nodules less than 1 cm in diameter. This discloses the potential of the algorithm for accurate characterizations of nodules (e.g., volume, change in volume over time) at an early stage, which can help to provide valuable guidance for further clinical management. (C) 1999 Society of Photo-Optical Instrumentation Engineers.

Abstract:   The objective of this work was to develop a segmentation technique for thickness measurements of the articular cartilage in MR images and to assess the interobserver reproducibility of the method in comparison with manual segmentation. The algorithm is based on a B-spline snakes approach and is able to delineate the cartilage boundaries in real time and with minimal user interaction. The interobserver reproducibility of the method, ranging from 3.3 to 13.6% for various section orientations and joint surfaces, proved to be significantly superior to manual segmentation. (C) 1999 Elsevier Science Inc.

Abstract:   It is now recognized in many domains that content-based image retrieval from a database of images cannot be carried out by using completely automated approaches. One such domain is medical radiology for which the clinically useful information in an image typically consists of gray level variations in highly localized regions of the image. Currently, it is not possible to extract these regions by automatic image segmentation techniques. To address this problem, we have implemented a human-in-the-loop (a physician-in-the-loop, more specifically) approach in which the human delineates the pathology bearing regions (PBR) and a set of anatomical landmarks in the image when the image is entered into the database. To the regions thus marked, our approach applies low-level computer vision and image processing algorithms to extract attributes related to the variations in gray scale, texture, shape, etc. In addition, the system records attributes that capture relational information such as the position of a PER with respect to certain anatomical landmarks. An overall multidimensional index is assigned to each image based on these attribute values. (C) 1999 Academic Press.

Abstract:   Abdominal organ segmentation is highly desirable but difficult, due to large differences between patients and to overlapping grey-scale values of the various tissue types. The first step in automating this process is to cluster together the pixels within each organ or tissue type. We propose to Form images based on second-order statistical texture transforms (Haralick transforms) of a CT or MRI scan. The original scan plus the suite of texture transforms are then input into a Hopfield neural network (HNN). The network is constructed to solve an optimization problem, where the best solution is the minima of a Lyapunov energy function. On a sample abdominal CT scan, this process successfully clustered 79-100% of the pixels of seven abdominal organs. It is envisioned that this Is the first step to automate segmentation. Active contouring (e.g., SNAKE's) or a back-propagation neural network can then be used to assign names to the clusters and fill in the incorrectly clustered pixels.

Abstract:   Videofluorography (VFG) using a barium-mixed bolus is in wide clinical use for assessing patients with swallowing disorders. VFG is usually done with both lateral (LA) and anterior-posterior (AP) views, most commonly in two separate sittings. A real-time, three-dimensional (3-D) representation of the evolution of a pharyngeal bolus and its volumetric information can potentially help clinicians analyze and visualize the kinematics of swallowing, dysphagia, and compensatory therapeutic strategies. Active contour models, also known as "Snakes," have been used to solve various image analysis and computer vision problems. We applied a Snake algorithm to automate in part the contour tracking and reconstruction of VFG images to visualize and quantitatively analyze the 3-D evolution of a pharyngeal bolus. To improve the accuracy of the Snake search, we provided the additional "knowledge" of the pharyngeal image itself, which served as an extra constraint to push the Snake curve toward the desired contour. VFG of pharyngeal bolus transport in a normal subject was recorded by using barium-mixed boluses (viscosity: 185 centipoise, density: 2.84 g/cc) with volumes of 5, 10, and 20 ml, The resulting LA and AP video images were digitally captured and matched frame by frame. The knowledge-based Snake search algorithm was used to generate Snake points to satisfy both internal (i.e., smoothness) and external (i.e., boundary fitting) constraints. Using these Snake points, we traced the 3-D bolus movement at each time instant, assuming elliptic geometry in the cross-section of the pharyngeal bolus. By concatenating the 3-D images for each time instant, we developed a 3-D movie representing pharyngeal bolus movement. The efficiency, reproducibility, and accuracy of this algorithm in tracing pharyngeal bolus boundaries and estimating front/tail velocities were assessed and found satisfactory. We conclude that 3-D pharyngeal bolus movement can be traced both accurately and efficiently by using a knowledge-based Snake search algorithm.

Abstract:   Due to their simplicity and flexibility, polygonal meshes are about to become the standard representation for surface geometry in computer graphics applications. Some algorithms in the context of multiresolution representation and modeling can be performed much more efficiently and robustly if the underlying surface tesselations have the special subdivision connectivity In this paper we propose a new algorithm for converting a given unstructured triangle mesh into one having subdivision connectivity. The basic idea is to simulate the shrink wrapping process by adapting the deformable surface technique known from image processing. The resulting algorithm generates subdivision