The classical approach of using minimum cut criterion for clustering is often ineffective due to the existence of outliers in the data. This paper presents a novel normalized graph sampling algorithm for clustering that improves the solution of clustering via the incorporation of a priori constraint in a stochastic graph sampling procedure. The quality of the proposed algorithm is empirically evaluated on two synthetic datasets and a color medical image database.
|Number of pages||4|
|Journal||Proceedings - International Conference on Pattern Recognition|
|Publication status||Published - 2002|
Scopus Subject Areas
- Computer Vision and Pattern Recognition