Identifying Diabetics Retinopathy using Deep Learning based Classification

Diabetic Retinopathy (DR) is one of the most common diabetic diseases found in most people. Deep learning methods have been used for the detection of proliferative and non-proliferative diabetic retinopathy. However, a significant deficiency of expert observers have provoked supercomputer assisted monitoring systems to identify the diabetic Retinopathy. The form of the vascular system of the human eye is a vital diagnostic factor in retinopathy. This work proposes the efficient detection of exudates and vessels from retinal images for retinal vasculature disorder analysis. Convolution Neural Network (CNN) is a type of artificial neural network used in image recognition and processing of retinal images after image processing steps to classify the retinal image. The proposed identifying diabetics by retinal image classification using ROI (Region of Interest) plays important roles in detection of some diseases in early stage diabetes by comparing its accuracy with existing methods such as the states of retinal blood vessels.