TY - GEN
T1 - Local features and kernels for classification of texture and object categories
T2 - 2006 Conference on Computer Vision and Pattern Recognition Workshops
AU - Zhang, Jianguo
AU - Marszałek, Marcin
AU - Lazebnik, Svetlana
AU - Schmid, Cordelia
PY - 2006
Y1 - 2006
N2 - 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 χ2 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.
AB - 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 χ2 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.
UR - http://www.scopus.com/inward/record.url?scp=33845513738&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33845513738&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2006.121
DO - 10.1109/CVPRW.2006.121
M3 - Conference contribution
AN - SCOPUS:33845513738
SN - 0769526462
SN - 9780769526461
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
BT - 2006 Conference on Computer Vision and Pattern Recognition Workshop
Y2 - 17 June 2006 through 22 June 2006
ER -