JFET_V2_N1_A1 G. Wiselin Jiji Dr. L. Ganesan Journal on Future Engineering and Technology 2230 – 7184 2 1 10 13 FCM, Eucledian distance, MRI brain image, Segmentation Segmentation is the most common way to identify various constituents of an image. In medical image visualization and analysis, segmentation is an indispensable step in the processing of images. In this paper, we propose an unsupervised fuzzy based segmentation to derive the homogeneity measure for partitioning the regions of the image during the process of segmentation. The proposed approach proceeds in 2 stages. Initially, a Fuzzy C-Mean algorithm is used to provide a partition of the image. In the second Stage, a decision process by applying a global analysis followed by a fine segmentation which is only focused on ambiguous points. The feasibility and effectiveness of the proposed method is evaluated with the various types of MRI brain images to identify the components of brain, in turn, used to locate the brain tumour and its growth rate. August-October 2006 Copyright © 2006 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=956