Journals Proceedings

Abstract

Medical image processing plays a key role in analyzing images taken though different diagnosing methods. The biological vision system is one of the most important means of exploration of the world to humans, performing complex tasks with great ease such as analysis, interpretation, recognition and pattern classification.Today there is an increase in interest for setting up medical system that can screen a large number of people for life threatening diseases, such as Cardio Vascular Diseases (CVD),Retinal disorders in Diabetic Patients. In this paper three different methods of segmentation are discussed. K-means and Fuzzy C-means (FCM) are two methods that use distance metric for segmentation. K-means is implemented using standard Euclidean distance metric, which is usually insufficient in forming the clusters. Instead in FCM, weighted distance metric utilizing pixel co-ordinates, RGB pixel color and/or intensity and image texture is commonly used. As the datasets scale increases rapidly it is difficult to use K-means and FCM to deal with massive data. So, the focus of this work is on the Morphological Watershed segmentation algorithm which gives good results on Blood vessel images of Atherosclerosis and Gradient Filter Techniques on retinal images. The tool used in this work is MATLAB.