Improving fuzzy c-means clustering based on local membership variation

The fuzzy c-means clustering algorithm has been successfully applied to a wide variety of problems. However, the image may be corrupted by noise, which leads to inaccuracy with segmentation. In the paper, a local fuzzy clustering regularization model is introduced in the objective function of the standard fuzzy c-means (FCM) algorithm. It can allow the membership of a pixel to be influenced by the memberships of its immediate neighborhood. Such schemes are useful for partition data sets affected by noise. Experimental results on both synthetic images and real image are given to demonstrate the effectiveness of the proposed algorithm.