Robust fuzzy c-means clustering algorithm with adaptive spatial & intensity constraint and membership linking for noise image segmentation

The fuzzy C-means (FCM) clustering method is proven to be an efficient method to segment images. However, the FCM method is not robustness and less accurate for noise images. In this paper, a modified FCM method named FCM_SICM for noise image segmentation is proposed. Firstly, fast bilateral filter is used to acquire local spatial & intensity information; secondly, absolute difference image between the original image and the bilateral filtered image is employed and the reciprocal of the difference image and the difference image itself constrain conventional FCM as well as the local spatial & intensity information respectively; finally, membership linking is achieved by summing all membership degrees calculated from previous iteration within every cluster in squared logarithmic form as the denominator of objective function. Experiments show that this proposed method achieves superior segmentation performance in terms of segmentation accuracy (SA), average intersection-overunion (mIoU), E-measure and number of iteration steps on mixed noise images compared with several state-of-the-art methods. (C) 2020 Elsevier B.V. All rights reserved.