Indexation et recherche de similarités avec des descripteurs structurés par coupes d’images sur des graphes
6 Novembre 2014
Catégorie : Soutenance de thèse
Image representation is a fundamental question for several computer vision tasks. The contributions discussed in my thesis extend the basic bag-of-words representations for the tasks of object recognition and image retrieval.
In the present thesis, we are interested in image description by structural graph descriptors. We propose a model, named bag-of-bags of words (BBoW), to address the problems of object recognition (for object search by similarity), and especially Content-Based Image Retrieval (CBIR) from image databases. The proposed BBoW model, is an approach based on irregular pyramid partitions over the image. An image is first represented as a connected graph of local features on a regular grid of pixels. Irregular partitions (subgraphs) of the image are further built by using graph partitioning methods. Each subgraph in the partition is then represented by its own signature. The BBoW model with the aid of graphs, extends the classical bag-of-words (BoW) model by embedding color homogeneity and limited spatial information through irregular partitions of an image.
Compared to existing methods for image retrieval, such as Spatial Pyramid Matching (SPM), the BBoW model does not assume that similar parts of a scene always appear at the same location in images of the same category. The extension of the proposed model to pyramid gives rise to a method we named irregular pyramid matching (IPM).
The experiments demonstrate the strength of our approach for image retrieval when the partitions are stable across an image category. The statistical analysis of subgraphs is fulfilled in the thesis. To validate our contributions, we report results on three related computer vision datasets for object recognition, (localized) content-based image retrieval and image indexing. The experimental results in a database of 13,044 general-purposed images demonstrate the efficiency and effectiveness of the proposed BBoW framework.
J’ai le plaisir de vous inviter à la soutenance de ma thèse, intitulée "Indexation et recherche de similarités avec des descripteurs structurés par coupes d’images sur des graphes" / "Indexing and Searching for Similarities of Images with Structural Descriptors via Graph-cuttings Methods" qui aura lieu le jeudi 20 novembre, 2014 du matin à 9:30 a.m. à l'amphithéâtre (Salle 050) du LaBRI, Univeristé de Bordeaux 1.
Address: Domaine universitaire, 351, cours de la Libération, 33405 Talence