Ant Colony Optimization Based Exudates Segmentation of Fundus Images

Abstract

Now a days, Diabetic Retinopathy is a deadly form of disease. Diabetic retinopathy is a complication of diabetes and a leading cause of blindness. It occurs when diabetes damages the tiny blood vessels inside the retina, the light-sensitive tissue at the back of the eye. Exudates of diabetic retinopathy appears as white or yellow in color. Early detection of diabetic retinopathy is not possible as patients are generally asymptomatic.  Exudates are frequently observed with microaneurysms. These methods are noise presence, low contrast, uneven illumination, and color variation. Therefore, in order to overcome the above stated issues computer aided diagnosis for exudates segmentation is needed. This proposed system first preprocesses the fundus image of human retina which is followed by image segmentation in which exudates are segmented. Proposed study segments the exudates using Ant Colony optimization Algorithm. The algorithm’s performance was evaluated with a dataset available online. Classification is performed on segmented image to classifying the image as Normal retina and diabetic retinopathy retina.