DMCA
Learning a Discriminative Classifier Using Shape Context Distances (2003)
Cached
Download Links
- [http.cs.berkeley.edu]
- [www.eecs.berkeley.edu]
- DBLP
Other Repositories/Bibliography
by
Hao Zhang
,
Jitendra Malik
| Citations: | 46 - 2 self |
BibTeX
@MISC{Zhang03learninga,
author = {Hao Zhang and Jitendra Malik},
title = {Learning a Discriminative Classifier Using Shape Context Distances},
year = {2003}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
For 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 benchmark dataset and is shown to outperform existing methods with far fewer prototypes.
