Dans cette thèse nous nous intéressons particulièrement à la détection de contours dans des images à niveaux de gris. Son objectif principal est la définition d'un critère de sélection des détecteurs de contours et leurs paramètres les plus appropriés pour mettre en évidence un contour donné par un utilisateur. Nous proposons une étude bibliographi...
Edge detection has acquired enormous importance in computer vision research: gaussian filter has been widely used in the past to accomplish this task. Although the gaussian filter has nice scaling behaviour and is computationally elegant, it suffers from the disadvantage of delocalisation of edges when operated at higher scales. Multi-scale process...
The problem of stereo vision is an ill-posed problem in the sense of Hadamard. Motivated by the work of Gamble et al. (1989), Clark and Yullie (1990), Toborg and Hwang (1990), and Barnard (1989), we formulate and setup the problem of stereo vision in an integrated multiresolution framework. The energy functions constructed are interactive in the se...
This research project is a study of the role of fixation and visual attention in object recognition. In this project, we build an active vision system which can recognize a target object in a cluttered scene efficiently and reliably. Our system integrates visual cues like color and stereo to perform figure/ground separation, yielding candidate regi...
Published in Advances in Psychology
In this synopsis of Chapter 4, first a brief introduction as well as an overview is given taking basic principles of and approaches to the modeling of visual perception from the information processing perspective into regard. Particularly, the emerging nexus of computational vision and computational neuroscience will be stressed given the indispens...
Despite its short history, the wavelet transform has found application in a remarkable diversity of disciplines: Mathematics, Physics, Numerical Analysis,Signal Processing and others. In this thesis, we explore applications of this transform in image analysis and devise several algorithms for recognising objects in an image of a scene. Five differe...
This thesis presents a learning based approach for detecting classes of objects and patterns with variable image appearance but highly predictable image boundaries. It consists of two parts. In part one, we introduce our object and pattern detection approach using a concrete human face detection example. The approach first builds a distribution-bas...
We describe a method for modeling object classes (such as faces) using 2D example images and an algorithm for matching a model to a novel image. The object class models are "learned'' from example images that we call prototypes. In addition to the images, the pixelwise correspondences between a reference prototype and each of the other prototypes m...
Ce document traite de plusieurs aspects de la vision stéréoscopique par ordinateur. Cette méthode consiste à partir d'une ou de plusieurs paires d'images à " reconstruire " une scène observée en trois dimensions, c'est-à-dire à produire une description des objets et surfaces observés ainsi que leur position dans l'espace. Le premier problème abordé...
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 b...
