Final year project on Diabetic retinopathy

ABSTRACT: Diabetic retinopathy (DR) is one of the leading disabling chronic diseases, and one of the leading causes of preventable blindness in the world. Early diagnosis of diabetic retinopathy enables timely treatment and in order to achieve it a major effort will have to be invested into screening programs and especially into automated screening programs. Through advanced image analysis techniques, retinal images are analysed for abnormalities that define and correlate with the severity of DR. For this purpose, features from the retinal images used are Blood Vessels, Exudates and Optic Disc. A through study is done in this area in recent days and based on that we had plotted many hypotheses. On the basis of hypothesis and the research happened on Diabetic retinopathy we had started designing the image processing model and the statistical model for the prediction model that is going to determine the severity of Diabetic retinopathy. In this duration we have been able to develop and estimate the data model for the blood vessel, optic disc and exudates features. The Designed system is open sourced and will be released to public domain under any open sourced licence so that our efforts are not limited to us. This makes development as well as maintenance of this system inexpensive and we will be able to provide user something valuable.