Abstract: Diabetic Retinopathy (DR) is a complication of diabetes that affects the eyes. It's caused by damage to the blood vessels of the light sensitive tissue at the back of the retina. The success rate of its curability solemnly depends on the early stage diagnosis or else it will lead to blindness. DR lesions are detected using Bag Of Visual Words (BoVW) model. Features are extracted using Speeded Up Robust Features (SURF).K-Means clustering is used for creating visual dictionary. Fisher vector encoding and Max pooling technique is used for creating Bag of Visual Words (BOVW). Finally SVM is used for lesion classification.