Annonce

Les commentaires sont clos.

Soutenance Chao ZHU - Effective and efficient visual description based on local binary patterns and gradient distribution for object recognition

27 Mars 2012


Catégorie : Soutenance de thèse


Soutenance de thèse de Chao ZHU intitulée "Effective and efficient visual description based on local binary patterns and gradient distribution for object recognition".

3 avril 2012, Ecole Centrale de Lyon.

 

Soutenance de thèse de Chao ZHU intitulée "Effective and efficient visual description based on local binary patterns and gradient distribution for object recognition".

La soutenance de Chao ZHU aura lieu le mardi 03 avril 2012 à 14h dans l’amphi 203 sur le site de l’École Centrale de Lyon (Ecully, près de Lyon).

Composition du jury

Pr. Matthieu CORD, LIP6 / Université Pierre et Marie Curie, France, Rapporteur,
Pr. Jenny BENOIS-PINEAU, LaBRI / Université Bordeaux 1, France, Rapporteur,
DR. Cordelia SCHMID, INRIA Rhone-Alps, France, Examinateur,
Pr. Liming CHEN, LIRIS / École Centrale de Lyon, France, Directeur de thèse,
Dr. Charles-Edmond BICHOT, LIRIS / École Centrale de Lyon, France, Co-directeur de thèse.

Résumé

Visual object recognition has become a very popular and important research topic in recent years because of its wide range of applications such as image/video indexing and retrieval, security access control, video monitoring, etc. Despite a lot of efforts and progress that have been made during the past years, it remains an open problem and is still considered as one of the most challenging problems in computer vision community, mainly due to inter-class similarities and intra-class variations like occlusion, background clutter, changes in viewpoint, pose, scale and illumination. Thus the first important step is to generate good visual description, which should be both discriminative and computationally efficient, while possessing some properties of robustness against the previously mentioned variations. In this context, the objective of this thesis is to propose some innovative contributions for object recognition task, in particular concerning several new visual features/descriptors to effectively and efficiently represent the visual content of objects for recognition. The proposed features/descriptors intend to capture an object's information from different aspects. More precisely, we propose multi-scale color local binary pattern (LBP) features to enhance the discriminative power and the photometric invariance property of the original LBP. We propose the orthogonal combination of local binary patterns (OC-LBP) for dimensionality reduction of LBP and use it for local image region description. We introduce the DAISY descriptor for the task of visual object recognition to efficiently capture the gradient information. We propose a novel local image descriptor called histograms of the second order gradients (HSOG) to capture the second order gradient information which are seldom investigated in the literature but proven useful for object recognition. The proposed approaches have been validated through comprehensive experiments conducted on several popular datasets such as Caltech 101 and PASCAL VOC.

Vous êtes chaleureusement conviés au pot qui suivra (bât E6, 2ème étage, salle de conférence).