A fuzzy evolutionary algorithm for medical image segmentation

Abstract

An unsupervised fuzzy clustering technique, fuzzy c-means (FCM) clustering algorithm has been widely used in image segmentation. However, the FCM algorithm always converges to strict local minima, starting from an initial guess of the membership degrees. To overcome this limitation of FCM algorithm, a fuzzy evolutional c-mean (FECM) algorithm is presented in this paper. We combine the classical FCM with an evolutional algorithm and we introduce the sharing operator for taking into account the spatial information.