Spatial credibilistic clustering algorithm in noise image segmentation

Abstract

An image segmentation algorithm based on credibilistic clustering algorithm incorporating spatial continuity is presented in this paper. The probabilistic constraint that the memberships of a pixel across clusters must sum to 1 in fuzzy c-means algorithm is removed, and credibility measure is introduced into image segmentation for the first time. By introducing a novel dissimilarity index in the credibilistic clustering algorithm objective function, the proposed algorithm is not only capable of utilizing local contextual information to impose local spatial continuity, but also allows the suppression of noise and helps to resolve classification ambiguity. Some important issues of the proposed algorithm are investigated, and the computational experiments are given to show the good performance of the proposed algorithm.