HAL : hal-00660300, version 1

DOI : 10.1016/j.imavis.2011.07.008

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

Image and Vision Computing 29 (2011) 716-729

Inexact graph matching based on kernels for object retrieval in image databases

Justine Lebrun 1, Philippe-Henri Gosselin 1, Sylvie Philipp-Foliguet 1

(18/08/2011)

In the framework of online object retrieval with learning, we address the problem of graph matching using kernel functions. An image is represented by a graph of regions where the edges represent the spatial relationships. Kernels on graphs are built from kernel on walks in the graph. This paper firstly proposes new kernels on graphs and on walks, which are very efficient for graphs of regions. Secondly we propose fast solutions for exact or approximate computation of these kernels. Thirdly we show results for the retrieval of images containing a specific object with the help of very few examples and counter-examples in the framework of an active retrieval scheme.

1 :	Equipes Traitement de l'Information et Systèmes (ETIS)
	CNRS : UMR8051 – ENSEA – Université de Cergy Pontoise

Domaine

:

Statistiques/Machine Learning Informatique/Recherche d'information

Mots Clés : Online – Interactive – Database – Content-Based – Object Retrieval – Image Retrieval – Machine Learning – Kernel Methods – Graph matching – Inexact match

hal-00660300, version 1

http://hal.archives-ouvertes.fr/hal-00660300

oai:hal.archives-ouvertes.fr:hal-00660300

Contributeur : Philippe-Henri Gosselin <>

Soumis le : Lundi 16 Janvier 2012, 13:43:27

Dernière modification le : Lundi 16 Janvier 2012, 14:09:32