Original Articles: 2016 Vol: 8 Issue: 1
Automated grading of diabetic retinopathy stages in fundus images using SVM classifer
Abstract
Medical image analysis is a very popular research area in these days in which digital images are analyzed for the diagnosis and screening of different medical problems. Diabetic Retinopathy (DR) is an eye disease caused by the increase of insulin in blood and may cause blindness. An automated system for the early detection of DR can save a patient vision and can also help the ophthalmologist in screening of DR which contains different types of lesion, i.e., microaneurysms, hemorrhages, exudates. This paper presents a method for detection and classification of exudates in colored retinal images. It eliminates the replication exudates region by removing the optic disc region. The detection of optic disc is indispensable for this approach which has been detected by Region of Interest (ROI) Kmeans clustering techniques. Exudates are found using their high gray level variation, and the classification of exudates is done with exudates features and SVM classifier. The proposed system is evaluated and tested on publicly available e-Optha-Ex database.