Mohammad Ali Balafar, A. R. Ramli, MASHOHOR, S.. Edge-preserving Clustering Algorithms and Their Application for MRI Image Segmentation. Lecture Notes in Engineering and Computer Science, 2180(1), 2010.
our lately defined edge-preserving neighborhood is used to improve an already exist extension for Fuzzy C-Mean (FCM). In the defined neighborhood, a window is centered on the pixel. Then, each sample, in the window, is considered the neighbor of the pixel if there is not any edge between the sample and the pixel. Moreover two extensions for Expectation Maximizing (EM) are introduced to have better clustering results in presence of noise. Promising experimental results of our proposed extensions in compare to two state-of-art extensions for FCM demonstrate the potential of proposed modifications. Index Terms—Neighborhood information, Brain segmentation.