Diagnosis of Advanced Diabetic Retinopathy from Fundus Image Using Machine Learning

Diabetic Retinopathy is an eye disease which mainly caused to the diabetic patients. The patients who have been suffering from diabetes since long time have major chances to suffer from Diabetic Retinopathy (DR) as well. If the DR is not detected early, the patient may experience vision loss, so early detection of this disease is very important. Micro-aneurysm and exudates are the features from which we can identify whether patients suffer from DR or not. Identifying retinal micro-aneurysms and exudates from the retinal fundus image is the primary goal of the proposed work to test for diabetic retinopathy. Firstly, the pre-processing is performed on Fundus image. Preprocessing techniques include adaptive median filtering, adaptive histogram equalization, and grey scale conversion. Feature extraction is utilized to extract the features from the fundus image after pre-processing. The extracted features are act as an input to the SVM classifier. The fundus image is classified as normal or impacted using a vector machine.