Date of Publication :27th December 2017

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 is one of the serious eye diseases that can cause blindness and vision loss.Diabetes mellitus, a metabolic disorder, has become one of the rapidly increasing health threats both in India and worldwide. Diabetic Retinopathy (DR) is an eye disease caused by the increase of insulin in the 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 the screening of DR which contains different types of lesion, i.e., microaneurysms, haemorrhages, exudates. Diabetic retinopathy is a vision-threatening complication as a result of diabetes mellitus which is the main cause of visual impairment and blindness in diabetic patients. In many cases, the patient is not conscious of the disease until it is too late for effective treatment. The prevalence of retinopathy varies with the age of diabetes and the duration of disease. Early diagnosis by regular screening and treatment is beneficial in preventing visual impairment and blindness. This project 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. Several image processing techniques including Image Enhancement, Segmentation, Classification, and registration has been developed for the early detection of DR on the basis of features such as blood vessels, exudes, haemorrhages and microaneurysms. This project presents a review of latest work on the use of image processing techniques for DR feature detection. Image Processing techniques are evaluated on the basis of their results. Exudates are found using their high grey level variation, and the classification of exudates is done with exudates features and SVM classifier.

Reference :