PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study
Jianguo Zhang, Marcin Marszalek, Svetlana Lazebnik and Cordelia Schmid
In: Beyond Patches workshop, in conjunction with CVPR(2006).

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 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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
ID Code:2310
Deposited By:Marcin Marszalek
Deposited On:16 November 2006