| Abstract |
|
Spectral segmentation has been shown to produce perceptually meaningful groupings. The underlying similarity matrices are usually very large. Several approximations - deterministic and stochastic - are used in practice. The approximations usually use only local information. It has been shown recently that a few random long-range interactions facilitate emergence of structure in several domains like Ising models. In this paper we explore the use of long-range interactions in spectral segmentation.
|
 Additional Information
|
Citation:
S. H. Srinivasan,
"Small-world Approximations in Spectral Segmentation,"
icpr,
pp. 36-39,
17th International Conference on Pattern Recognition (ICPR'04) - Volume 2,
2004
|
