Local features and kernels for classification of texture and object categories: a comprehensive study

Jianguo Zhang 1 Marcin Marszalek 1 Svetlana Lazebnik 2 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as distributions (signatures or histograms) of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover's Distance and the chi-square distance. We first evaluate the performance of our approach with different keypoint detectors and descriptors, as well as different kernels and classifiers. We then conduct a comparative evaluation with several state-of-the-art recognition methods on four texture and five object databases. On most of these databases, our implementation exceeds the best reported results and achieves comparable performance on the rest. Finally, we investigate the in influence of background correlations on recognition performance via extensive tests on the PASCAL database, for which ground-truth object localization information is available. Our experiments demonstrate that image representations based on distributions of local features are surprisingly effective for classification of texture and object images under challenging real-world conditions, including significant intra-class variations and substantial background clutter.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2007, 73 (2), pp.213-238. 〈10.1007/s11263-006-9794-4〉
Liste complète des métadonnées

Littérature citée [63 références]  Voir  Masquer  Télécharger


https://hal.archives-ouvertes.fr/hal-00171412
Contributeur : Thoth Team <>
Soumis le : mardi 19 avril 2011 - 10:12:29
Dernière modification le : mercredi 11 avril 2018 - 01:58:23
Document(s) archivé(s) le : mercredi 20 juillet 2011 - 02:20:08

Fichiers

ZhangMarszalekLazebnikSchmid-I...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Jianguo Zhang, Marcin Marszalek, Svetlana Lazebnik, Cordelia Schmid. Local features and kernels for classification of texture and object categories: a comprehensive study. International Journal of Computer Vision, Springer Verlag, 2007, 73 (2), pp.213-238. 〈10.1007/s11263-006-9794-4〉. 〈hal-00171412〉

Partager

Métriques

Consultations de la notice

3980

Téléchargements de fichiers

2848