Identification of ischemic stroke by marker controlled watershed segmentation and fearture extraction

Abstract

In this paper, we will describe a method that distinguishes the ischemic stroke from Computed Tomography (CT) brain images by extracting the statistical and textural features. First, preprocessing of the CT images is done followed by image enhancement. Segmentation of the CT images is performed by Marker Controlled Watershed. After the segmentation, we get the Grey Level Co-occurrence matrix (GLCM) and extract the textural and statistical features. The disadvantage of watershed is the over-segmentation caused by noise and solved by Marker Controlled Watershed as shown experimentally. The features extracted are contrast, correlation, standard deviation, variance, homogeneity, energy and mean. We noticed in our results that the values of homogeneity, energy and mean are bigger in normal CT images than in abnormal CT images where the contrast, correlation, standard deviation and variance of normal CT images are less than those of abnormal CT images (Ischemic Stroke).