HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation

Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study

Jianguo Zhang 1 Marcin Marszałek 1 Svetlana Lazebnik 2 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
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 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.
Document type :
Complete list of metadata

Cited literature [53 references]  Display  Hide  Download

Contributor : Rapport de Recherche Inria Connect in order to contact the contributor
Submitted on : Friday, May 19, 2006 - 7:54:24 PM
Last modification on : Wednesday, February 2, 2022 - 3:58:14 PM
Long-term archiving on: : Sunday, April 4, 2010 - 8:49:40 PM


  • HAL Id : inria-00070281, version 1



Jianguo Zhang, Marcin Marszałek, Svetlana Lazebnik, Cordelia Schmid. Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study. [Research Report] RR-5737, INRIA. 2005, pp.39. ⟨inria-00070281⟩



Record views


Files downloads