A fast anti-noise fuzzy C-means algorithm for image segmentation

Conventional fuzzy C-means (FCM) algorithm does not consider spatial information in the clustering, which makes it sensitive to noise and inefficient. In order to overcome these problems, we propose a fast anti-noise FCM algorithm for image segmentation, which constructs a new spatial function by combining pixel gray value similarity and membership. This spatial function is used to update the membership which in turn is used to obtain the cluster centers iteratively. The proposed algorithm can achieve desirable segmentation results in less iterations and reduce the effect of noise effectively. Experimental results show that the proposed algorithm outperforms conventional FCM and other extended FCM algorithms.