Abstract—Diabetic retinopathy is an ailment of the retinal vasculature that ultimately develops to some diploma in nearly all patients with lengthy-status diabetes. Proliferative diabetic retinopathy is an uncommon circumstance in all likelihood to cause acute visual deficiency. It is observed via the growth of unusual new retinal vessels. To symbolize the improvement of irregular new retinal vessels, an algorithm for spontaneously identifying new vessels on the optic disc using retinal photographs is described. The algorithm takes Five module method (FMM) compressed retinal images as the input. Watershed lines and canny detectors are used to find the vessel like candidate segment. Different features namely shape of the segment, position of the segment from the origin, positioning, intensity of the segment in the image, divergence, and line density are extracted for each candidate segment. Each candidate segment is labeled as normal or abnormal based on its features using Support Vector Machine (SVM) classifier. The experimentation results suggests that the automated retinopathy analysis system provides clinical insights in detecting the ailment. Index Terms—Five modules Method, Watershed lines, Canny edge detection, Support Vector Machine, Retinal image, Optic disc, Optic vessel. I. INTRODUCTION METHOD is introduced to decide the advent of vessels in progression levels that lead to visual impairment. The system accepts the retinal images from the user. The image must be taken in high resolution since the result depends on the quality of the image. First step is to preprocess the input image. Then the image is segmented to ease the process of classification. The result obtained from the segmentation phase is later classified as normal or abnormal using SVM. The optic Akshay S is with Department of Computer Science, Amrita School of Arts and Sciences, Amrita Vishwa Vidyapeetham, Mysore Campus, Amrita University, Karnataka, India.( e-mail: s_akshay@asas.mysore.amrita.edu). Apoorva P is with Department of Computer Science, Amrita School of Arts and Sciences, Amrita Vishwa Vidyapeetham, Mysore Campus, Amrita University, Karnataka, India.(phone 0821 - 2343479/80; e-mail: p_apoorva@asas.mysore.amrita.edu). disk is tracked by combining blood vessels and color properties. Initially vessel like candidate segments are detected using a method based on watershed lines fifteen features that are related to different aspects of the retinal image. Depending on these features later the segmented retinal image is classified as normal or abnormal. In order to build an effective tool to detect the defects in retina it is very essential to understand the process of image formation in the eye. A study on how the human eye vision is limited in various aspects and how a digital image also represents similar limitations plays a vital role. So, it is important to map the similarity in the way in which human beings and the electronic imaging devices understand the resolution and how the changes in the illuminations are recognized by them. The shape of a human eye is almost a sphere with an approximate 22mm in diameter. The surface of the eye is covered by a tough transparent tissue called cornea. Next to cornea there exists sclera, is a membrane that covers the remaining of the optic disc. Choroid is a layer that lies below the sclera. A network of blood vessel is contained by choroid which serves as the supplier of nutrition to the eye. The choroid is made up of majorly two parts such as ciliary body and iris. The iris which is the central opening of the body which is 2mm to 8 mm in diameter. The forward-facing portion of the visible pigment is characterized by observable pigment and the rear portion by black pigment. The lens of the eye contains fibrous cells which make up concentric layers that are connected to the ciliary body. It contains 60 percent of water and about 6 percent fat, and remaining parts made up with proteins that is present in the highest amount than any other tissue in the eye. The last and the inner more layer of the eye is called retina. Retina contains two types of receptors that identifies the illuminations such as cones and rods. There are approximately around 6 to 7 million cones present in the center part of the retina and are called as fovea which are very reactive to colors. The eye is controlled by muscles that swings the eye ball so that the image or illumination of what is viewed by the eye falls on the fovea. Approximately 150 million rods are distributed over the retinal layer. They are responsible for Segmentation and Classification of FMM Compressed Retinal Images Using Watershed and Canny Segmentation and Support Vector Machine Akshay S and Apoorva P A 1035 International Conference on Communication and Signal Processing, April 6-8, 2017, India 978-1-5090-3800-8/17/$31.00 ©2017 IEEE