Discovery - University of Dundee - Online Publications

Library & Learning Centre

Local features and kernels for classification of texture and object categories

Local features and kernels for classification of texture and object categories: a comprehensive study

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations

Authors

Research units

Info

Original languageEnglish
Title of host publicationConference on Computer Vision and Pattern Recognition Workshop, 2006
Subtitle of host publication(CVPRW'06)
EditorsCordelia Schmid, Stefano Soatto, Carlo Tomasi
PublisherIEEE
Pages93-100
Number of pages8
ISBN (Print)0769526462
DOIs
StatePublished - 2006
EventIEEE Computer Society, 2006 Conference on Computer Vision and Pattern Recognition (CVPRW'06) - New York, United States

Conference

ConferenceIEEE Computer Society, 2006 Conference on Computer Vision and Pattern Recognition (CVPRW'06)
CountryUnited States
CityNew York
Period17/06/0622/06/06

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 ÷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.

Documents

Library & Learning Centre

Contact | Accessibility | Policy