Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

Résumé

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 ÷2 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 4 texture and 5 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 influence of background correlations on recognition performance.
Fichier principal
Vignette du fichier
ZhangMarszalekLazebnikSchmid-BP06-ClassificationStudy.pdf (936.95 Ko) Télécharger le fichier
Vignette du fichier
feanker.png (334.09 Ko) Télécharger le fichier
ZhangMarszalekLazebnikSchmid-BP06-ClassificationStudy-slides.pdf (5.85 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Format : Autre

Dates et versions

inria-00548574 , version 1 (20-12-2010)

Identifiants

Citer

Jianguo Zhang, Marcin Marszałek, Svetlana Lazebnik, Cordelia Schmid. Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study. Conference on Computer Vision and Pattern Recognition Workshop (Beyond Patches workshop, CVPR '06), Jun 2006, Washington, United States. pp.13, ⟨10.1109/CVPRW.2006.121⟩. ⟨inria-00548574⟩
3962 Consultations
858 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More