DMCA
Local features and kernels for classification of texture and object categories: a comprehensive study (2007)
Cached
Download Links
| Venue: | International Journal of Computer Vision |
| Citations: | 639 - 33 self |
BibTeX
@ARTICLE{Zhang07localfeatures,
author = {J. Zhang and S. Lazebnik and C. Schmid},
title = {Local features and kernels for classification of texture and object categories: a comprehensive study},
journal = {International Journal of Computer Vision},
year = {2007},
volume = {73},
pages = {2007}
}
Share
 |
 |
 |
 |
||
OpenURL
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 χ 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 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.
Keyphrases
local feature object category comprehensive study several state-of-the-art recognition method extensive test comparative evaluation object database sparse set local image feature significant intra-class variation substantial background clutter image representation ground-truth object localization information pascal database recognition performance different keypoint detector object recognition task effective measure earth mover large-scale evaluation comparable performance reported result object image keypoint location support vector machine classifier different kernel real-world condition background correlation
