New robust fuzzy c-means based gaussian function in classifying brain tissue regions

Abstract

This paper introduces a new fuzzy c-mean objective function called Kernel induced Fuzzy C-Means based Gaussian Function for the purpose of segmentation of brain medical images. It obtains effective methods for calculating memberships and updating prototypes by minimizing the new objective function of Gaussian based fuzzy c-means. The performance of proposed algorithm has been tested with synthetic image and then it has been implemented for segmenting the brain [18] medical images to reduce the inhomogeneities and to allow the labeling of a pixel (voxel) to be influenced by the labels in its immediate neighborhood. Also this paper compares the results of proposed method with the results of existing basic Fuzzy C-Means. © 2009 Springer Berlin Heidelberg.