Abstract: Research in the field of medicine suggests that abnormal pressure and glucose levels are a major cause of several critical complaints. A retinal image provides a snapshot of what is happening inside the human body. In particular, the state of the retinal vessels has been shown to reflect the cardiovascular condition of the body. Retinal images provide considerable information on pathological changes caused by local ocular disease which reveals diabetes, hypertension, arteriosclerosis, cardiovascular disease and stroke. Computer-aided analysis of retinal image plays a central role in diagnostic procedures. However, automatic retinal segmentation is complicated by the fact that retinal images are often noisy, poorly contrasted, and the vessel widths can vary from very large to very small. In this paper, we place focus to implement automate segmentation approach based on graph theoretical method. The scope of this paper is to provide blood vessels regional information by the measure of median filter algorithm. We proposed a novel computational approach for the segmented vascular structure as a vessel segment graph and solve the problem to identify vessels as the one of the findings of blood vessels in the graph given a set of constraints such as CRAE and CRVE. These measurements are found to have good correlation with hypertension, coronary heart disease, and stroke. Moreover, these require the accurate extraction of distinct vessels from a retinal image and a classification method is used to reveals the optimization problem and evaluate it on a real-world dataset of retinal images.

Keywords: Automatic segmentation, Computational approach, Classification Data mining.