DIABETIC RETINOPATHY DETECTION

Abstract: In today’s world, Diabetes may be a quite common disease which affects tons of people’s health. As the number of diabetic patients is increasing significantly in India, there is a rise in numerous associated diseases that have disturbed the society. Diabetic Retinopathy (DR) is taken into account to be one among such silent diseases which occur as results of either Type 1 or Type 2 diabetes. Late diagnosis of this disease may cause permanent eye blindness. Thus, for early diagnosis of Diabetic Retinopathy, a software-based algorithm is meant here. This technique are often promising for the pre-detection of DR with none involvement of an expert doctor and hence will save both time and money. Here, CNN based image processing is used which exploits the knowledge of Computer Science and Biomedical Engineering to identify whitish lesions, cotton wool spots and hard exudates associated with DR. Based on the worth of pixel counts, the image of the patient’s eye under examination is assessed as a Diabetic Retinopathy eye or a Non-Diabetic Retinopathy eye.

Keywords: Amazon Web Server, Digital Ocean Server, Puttygen.exe, Putty.exe, Winscp