New Method for Image Segmentation

in this paper we describe a modified segmentation method applied to image. An EM algorithm is developed to estimate parameters of the Gaussian mixtures. Recently, researchers are focusing more on the study of expectation of maximization (EM) due to its useful applications in a number of areas, such as multimedia, image processing, pattern recognition and bioinformatics. The human visual system can often correctly interpret images that are of quality that they contain insufficient explicit information to do so. The difficulty is mainly due to variable brain structures, various MRI artifacts and restrictive body scanning methods. The IBSR image segmentation data set is used to compare and evaluate the proposed methods. In this paper, we propose a modified expectation of maximization (MEM) based on the properties of likelihood, while reducing number of iteration for a sick of fast converge to the center of cluster and your application to image segmentation. The experiments on real images show that: (1) our proposed approach can reduce the number of iterations, which leads to a significant reduction in the computational cost while attaining similar levels of accuracy. (2) The approach also works well when applied to image segmentation. A methodology for calculate is presented for making use the error between the ground truth, human-segmented image data sets to compare, develop and optimize image segmentation algorithms. This error measure is based on object-by-object comparisons of a segmented image and a ground-truth (reference) image. Experimental results for segmented images demonstrate the good segmentation performance of the proposed approach. (C) 2015 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).