Robust matching and recognition using context-dependent kernels

Hichem Sahbi 1 Jean-Yves Audibert 2, 3 Jaonary Rabarisoa 3, 2 Renaud Keriven 3, 2
3 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : The success of kernel methods including support vector machines (SVMs) strongly depends on the design of appropriate kernels. While initially kernels were designed in order to handle fixed-length data, their extension to unordered, variable-length data became more than necessary for real pattern recognition problems such as object recognition and bioinformatics. We focus in this paper on object recognition using a new type of kernel referred to as "context-dependent". Objects, seen as constellations of local features (interest points, regions, etc.), are matched by minimizing an energy function mixing (1) a fidelity term which measures the quality of feature matching, (2) a neighborhood criteria which captures the object geometry and (3) a regularization term. We will show that the fixed-point of this energy is a "context-dependent" kernel ("CDK") which also satisfies the Mercer condition. Experiments conducted on object recognition show that when plugging our kernel in SVMs, we clearly outperform SVMs with "context-free" kernels.
Type de document :
Communication dans un congrès
Liste complète des métadonnées
Contributeur : Pascal Monasse <>
Soumis le : lundi 17 juin 2013 - 17:11:38
Dernière modification le : mercredi 20 février 2019 - 14:41:48


  • HAL Id : hal-00834980, version 1


Hichem Sahbi, Jean-Yves Audibert, Jaonary Rabarisoa, Renaud Keriven. Robust matching and recognition using context-dependent kernels. ICML, Jul 2008, Helsinki, Finland. pp.856-863. ⟨hal-00834980⟩



Consultations de la notice