Innovative feature set for retinopathic analysis of diabetes and its detection

A fully automated approach is presented for the feature selection for the application in diabetic retinopathy. Diabetic Retinopathy(DR) is a vascular disorder affecting the retina due to prolonged diabetes. It can lead to sudden vision loss due to DR.This work is aimed to develop an automated system to analyze the retinal images for extracting important features of diabetic retinopathy using the image processing techniques. The color retinal images are segmented following the pre-processing steps, i,e color normalization and contrast enhancement. The entire segmented images establish a dataset of regions. To classify these segmented regions into varying changes in blood vessels and different finding such as exudates, microaneurysms, a set of features such as color, size, edge strength and texture are extracted which can be used as part of an automated diabetes recognition system.