This paper presents a novel variational framework to deal with frame partition problems in Computer Vision. This framework exploits boundary and region-based segmentation modules under a curve-based optimization objective function. The task of supervised texture segmentation is considered to demonstrate the potentials of the proposed framework. The textured feature space is generated by filtering the given textured images using isotropic and anisotropic filters, and analyzing their responses as multi-component conditional probability density functions. The texture segmentation is obtained by unifying region and boundary-based information as an improved Geodesic Active Contour Model. The defined objective function is minimized using a gradient-descent method where a level set approach is used to implement the obtained PDE. According to this PDE, the curve propagation towards the final solution is guided by boundary and region-based segmentation forces, and is constrained by a regularity force. The level set implementation is performed using a fast front propagation algorithm where topological changes are naturally handled. The performance of our method is demonstrated on a variety of synthetic and real textured frames.

This paper describes a new approach to adaptive estimation of parametric deformable contours based on B-spline representations. The problem is formulated in a statistical framework with the likelihood function being derived from a region -based image model. The parameters of the image model, the contour parameters, and the B-spline parameterization order (i.e., the number of control points) are all considered unknown. The parameterization order is estimated via a minimum description length (MDL) type criterion. A deterministic iterative algorithm is developed to implement the derived contour estimation criterion. The result is an unsupervised parametric deformable contour: it adapts its degree of smoothness/complexity (number of control points) and it also estimates the observation (image) model parameters. The experiments reported in the paper, performed on synthetic and real (medical) images, confirm the adequacy and good performance of the approach.

. A standard method for handling Bayesian models is to use Markov chain Monte Carlo methods to draw samples from the posterior. We demonstrate this method on two core problems in computer vision---structure from motion and colour constancy. These examples illustrate a samplers producing useful representations for very large problems. We demonstrate that the sampled representations are trustworthy, using consistency checks in the experimental design. The sampling solution to structure from motion is strictly better than the factorisation approach, because: it reports uncertainty on structure and position measurements in a direct way; it can identify tracking errors; and its estimates of covariance in marginal point position are reliable. Our colour constancy solution is strictly better than competing approaches, because: it reports uncertainty on surface colour and illuminant measurements in a direct way; it incorporates all available constraints on surface reflectance and on illumination in a direct way; and it integrates a spatial model of reflectance and illumination distribution with a rendering model in a natural way. One advantage of a sampled representation is that it can be resampled to take into account other information. We demonstrate the effect of knowing that, in our colour constancy example, a surface viewed in two different images is in fact the same object. We conclude with a general discussion of the strengths and weaknesses of the sampling paradigm as a tool for computer vision. Keywords: Markov chain Monte Carlo, colour constancy, structure from motion 1.

In this paper we propose an approach to vehicle classification under a mid-field surveillance framework. We develop a repeatable and discriminative feature based on edge points and modified SIFT descriptors, and introduce a rich representation for object classes. Experimental results show the proposed approach is promising for vehicle classification in surveillance videos despite great challenges such as limited image size and quality and large intra-class variations. Comparisons demonstrate the proposed approach outperforms other methods. 1.

This thesis describes an online search engine for 3D models, focusing on query interfaces and their corresponding model/query representations and matching methods. A large number of 3D models has already been created, many of which are freely available on the web. Because of the time and e#ort involved in creating a highquality 3D model, considerable resources could be saved if these models could be reused. However, finding the model you need is not easy, since most online models are scattered across the web, on repository sites, project sites, and personal homepages. To make these models more accessible, we have developed a prototype 3D model search engine. This project serves as a test bed for new methods in web crawling, query interfaces, and matching of 3D models. This thesis focuses on query interfaces and their accompanying matching methods. We investigated query interfaces based on text keywords, 3D shape, 2D shape, and some combinations.

In this paper, we investigate the use of the Bayesian inference for some detection and classification problems of great importance in sonar imagery. More precisely this paper is concerned with the segmentation of sonar image, the classification of object lying on the sea-bottom and the classification of sea-floor. These aforementioned classification tasks are based on the identification of the detected cast shadows which correspond to a lack of acoustic reverberation behind the different natural or man-made objects lying on the sea-floor. The adopted Bayesian approach allows to model efficiently all the available prior information, for each detection and classification task under concern yielding a cost minimization problem. To this end, we associate to each Bayesian statistical modeling, a specific optimization strategy well suited to the global energy function to be minimized. These segmentation and classification schemes can be used separately for a specific application or can lead ...

Due to the difficulty of character segmentation in cursive handwriting recognition, much recent research has turned to segmentation free approaches of word recognition. While techniques of feature extraction for presegmented characters have been thoroughly explored in the literature, an evaluation of features for use with segmentation during recognition techniques remains sparse. The main purpose of this thesis is to provide a comparison of a number of feature extraction techniques applied to the domain of legal amount recognition in bank checks. An experimental system using Hidden Markov Models and a horizontally sliding window is described. Results are presented for the recognition of the entire legal field using a variety of features. Of the experiments presented here, the best results were obtained by concatenating the feature vectors from the present, previous, and next window...

Deformable Template models are first applied to track the inner wall of coronary arteries in intravascular ultrasound sequences, mainly in the assistance to angioplasty surgery. A circular template is used for initializing an elliptical deformable model to track wall deformation when inflating a balloon placed at the tip of the catheter. We define a new energy function for driving the behavior of the template and we test its robustness both in real and synthetic images. Finally we introduce a framework for learning and recognizing spatio-temporal geometric constraints based on Principal Component Analysis (eigenconstraints). 1

Abstract — We present an approach for vehicle classification in IR video sequences by integrating detection, tracking and recognition. The method has two steps. First, the moving target is automatically detected using a detection algorithm. Next, we perform simultaneous tracking and recognition using an appearance-model based particle filter. We present a probabilistic algorithm for tracking and recognition that incorporates robust template matching and incremental subspace update. There are two template matching methods used in the tracker: one is robust to small perturbation and the other to background clutter. Each method yields a probability of matching. The templates are represented using mixed probabilities and updated when the appearance models cannot adequately represent the variations in object appearance. We also model the tracking history using a nonlinear subspace described by probabilistic kernel principal components analysis, which provides a third probability. The most-recent tracking result is incrementally integrated into the nonlinear subspace by augmenting the kernel Gram matrix with one row and one column. The product of the three probabilities is defined as the observation likelihood used in a particle filter to derive the tracking and recognition result. The tracking result is evaluated at each frame. Low confidence in tracking performance initiates a new cycle of detection, tracking and classification. We demonstrate the robustness of the proposed method using outdoor IR video sequences. Index Terms — detection, tracking, recognition, tracking evaluation, IR video

This article describes a novel way of representing large databases of shapes. We propose a hierarchical clustering of a set of Fouriertransformed contours. The clustering analysis is density-based and is performed using topographic maps. We have tested the approach on a database of extracted contours of marine animals, generated by Mokhtarian and co-workers. The resulting clusters group contours that show similar global shapes, which sometimes differ from those grouped by Mokhtarian and co-workers, due to a difference in similarity criterion.