This thesis belong to the field of modelisation and recognition of objects using their appearance. Each object is modeled by a collection of images and recognition is obtained by the matching between a new image and a model image. Images are modeled by measures on local features. Several local descriptor bases are theoretically and experimentally evaluated and a Gaussian derivative basis is selected for its properties which include~: high discriminability for a concise description, scalability and steerability. Invariance to orientation is obtained by setting derivative directions according to the local gradient. Invariance to scale is obtained by a new technique which locally selects a characteristic scale for describing a neighborhood. Th...
Soutenue par les progrès récents et rapides des techniques d'acquisition 3D, la reconnaissance d'obj...
There has been strong research interest in 3D object recognition over the last decade, due to the pr...
Pour chaque partie il existe un résumé en français et en anglais.This thesis deals with the recognit...
This thesis belong to the field of modelisation and recognition of objects using their appearance. E...
This work belongs to the class of appearance based object modeling and recognition through local des...
In this thesis we explore a new image description method composed of a multi-scale vector of Laplaci...
International audienceIn this paper we propose a comprehensive framework that allows existing local ...
Local features have become an essential tool in visual recognition. Much of the progress in computer...
During the last few years, there has been a growing interest in object recognition schemes directly ...
We introduce a new method that characterizes quantitatively local image descriptors in terms of thei...
Object recognition is one of the most active fields of computer vision. In this thesis we consider t...
In this thesis, we first present a contribution to overcome this problem of robustness for the recog...
This paper describes the investigation of techniques for sampling, representing and matching the app...
We introduce a new method that characterizes typical local image features (e.g., SIFT [9], phase fea...
Soutenue par les progrès récents et rapides des techniques d'acquisition 3D, la reconnaissance d'obj...
There has been strong research interest in 3D object recognition over the last decade, due to the pr...
Pour chaque partie il existe un résumé en français et en anglais.This thesis deals with the recognit...
This thesis belong to the field of modelisation and recognition of objects using their appearance. E...
This work belongs to the class of appearance based object modeling and recognition through local des...
In this thesis we explore a new image description method composed of a multi-scale vector of Laplaci...
International audienceIn this paper we propose a comprehensive framework that allows existing local ...
Local features have become an essential tool in visual recognition. Much of the progress in computer...
During the last few years, there has been a growing interest in object recognition schemes directly ...
We introduce a new method that characterizes quantitatively local image descriptors in terms of thei...
Object recognition is one of the most active fields of computer vision. In this thesis we consider t...
In this thesis, we first present a contribution to overcome this problem of robustness for the recog...
This paper describes the investigation of techniques for sampling, representing and matching the app...
We introduce a new method that characterizes typical local image features (e.g., SIFT [9], phase fea...
Soutenue par les progrès récents et rapides des techniques d'acquisition 3D, la reconnaissance d'obj...
There has been strong research interest in 3D object recognition over the last decade, due to the pr...
Pour chaque partie il existe un résumé en français et en anglais.This thesis deals with the recognit...