Learning segmentation by random walks (2000)
Cached
Download Links
- [www.stat.washington.edu]
- [www.cs.cmu.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | In Advances in Neural Information Processing |
| Citations: | 78 - 4 self |
BibTeX
@INPROCEEDINGS{Shi00learningsegmentation,
author = {Jianbo Shi},
title = {Learning segmentation by random walks},
booktitle = {In Advances in Neural Information Processing},
year = {2000},
pages = {470--477},
publisher = {MIT Press}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Abstract We present a new view of image segmentation by pairwise similarities. We interpret the similarities as edge flows in a Markov random walk and study the eigenvalues and eigenvectors of the walk's transition matrix. This interpretation shows that spectral methods for clustering and segmentation have a probabilistic foundation. In particular, we prove that the Normalized Cut method arises naturally from our framework. Finally, the framework provides a principled method for learning the similarity function as a combination of features. 1 Introduction Among the most successful methods in image segmentation combine a global optimality segmentation criterion with local similarity features[3]. Similarity between two pixels i; j is defined as a positive function Sij depending on the local image properties of the pixels(e.g. color, texture, edge flow). Local features are not only computationally convenient, they are also supported by neurological evidence about the human perception of shapes.
