Welcome to IEEE Xplore 2.0: Learning a discriminative classifier using shape context distances

Cart | Sitemap | Help

Abstract


	BROWSE	SEARCH	IEEE XPLORE GUIDE	SUPPORT

View TOC

Learning a discriminative classifier using shape context distances
Hao Zhang Malik, J.
Comput. Sci. Div., Univ. of California at Berkeley, CA, USA;

This paper appears in: Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on
Publication Date: 18-20 June 2003
Volume: 1, On page(s): I-242- I-247 vol.1
ISSN: 1063-6919
ISBN: 0-7695-1900-8
INSPEC Accession Number: 7769567
Current Version Published: 2003-07-15

Abstract
For the purpose of object recognition, we learn one discriminative classifier based on one prototype, using shape context distances as the feature vector. From multiple prototypes, the outputs of the classifiers are combined using the method called "error correcting output codes". The overall classifier is tested on a benchmark dataset and is shown to outperform existing methods with far fewer prototypes.

Index Terms
Available to subscribers and IEEE members.

References
Available to subscribers and IEEE members.

Citing Documents
Available to subscribers and IEEE members.

You are not logged in.

Guests may access Abstract records free of charge.