Image Categorization by Learning and Reasoning with Regions (2004)
Cached
Download Links
- [www.jmlr.org]
- [www.ai.mit.edu]
- [www.ai.mit.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | Journal of Machine Learning Research |
| Citations: | 98 - 7 self |
BibTeX
@ARTICLE{Chen04imagecategorization,
author = {Yixin Chen and James Z Wang and Donald Geman},
title = {Image Categorization by Learning and Reasoning with Regions},
journal = {Journal of Machine Learning Research},
year = {2004},
volume = {5},
pages = {913--939}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Designing computer programs to automatically categorize images using low-level features is a challenging research topic in computer vision. In this paper, we present a new learning technique, which extends Multiple-Instance Learning (MIL), and its application to the problem of region-based image categorization. Images are viewed as bags, each of which contains a number of instances corresponding to regions obtained from image segmentation. The standard MIL problem assumes that a bag is labeled positive if at least one of its instances is positive; otherwise, the bag is negative.
