Detection and Classification of Diabetic Retinopathy by Fuzzy Based Decision-Making System

In India, there are estimated 77 million people above the age of 18 years are suffering from diabetes mellitus and nearly 25 million are prediabetics. Diabetic Retinopathy(DR) is an eye disease which occur due to damage of retina as a result of long illness of diabetes mellitus. Severe of this disease doesn’t have any treatment. It leads to vision loss. So, this paper proposed to detect the disease in early stage by fuzzy logic method using image processing techniques. It is characterized by the presence of different lesions referred to as dark or red lesion, such as micro aneurysms and hemorrhages and bright lesion such as exudates. There are four stages of diabetic retinopathy such as i)Mild DR ii)Moderate DR iii)Severe DR iv)Proliferative DR. This proposed technique is implemented using MATLAB with improved accuracy of 86% and precision is 90%.