Skip to Main Content
With an expert system, a novel fuzzy c-means clustering method based on PSO and expert system (PSFCM-ES) is proposed in this paper. The algorithm is formulated by incorporating the spatial neighborhood information into the standard FCM clustering algorithm. The k-nearest neighbor (k-NN) algorithm is introduced for calculating the weight in the spatially weighted FCM algorithm so as to improve the performance of image clustering. To speed up the FCM algorithm, the iteration is carried out with the gray level histogram of image instead of the conventional whole data of image. PSO algorithm is included to select optimal cluster centers and expert system is also introduced to solve the labeling problems. Experimental results indicate the proposed approach is effective and efficient.
Date of Conference: 16-18 May 2008