Brain Mri image segmentation using improved sobel method

Abstract

Health care applications need correct segmentation on medical images which helps for correct diagnosis. Good quality segmentation can be done only by an efficient method. In this paper we have studied and evaluated three different segmentation techniques. We have presented an improved edge segmentation method for brain MRI images. The improved sobel algorithm makes use of sobel method with closed contour algorithm which will combinely help in maintaining uniformity in the regions. Image dependent method of thresholding helps in closed contour to fix up clear boundaries of different regions in an image. The algorithm is implemented in Matlab and performance is measured subjectively as well as objectively. For comparative analysis, we have used entrophy, correlation and energy of the three segmentations which show improved sobel method is better compared to watershed segmentation and sobel segmentation.