Diabetic Retinopathy (DR) is an eye disease that can affect people with diabetes. It is the most common cause of vision loss among people with diabetes and the leading cause of vision impairment and blindness among working-age adults. However, if it is treated properly during its initial stages, the chance of blindness is reduced thereby signifying the importance of its detection. Digital color fundus images are becoming increasingly important for the diagnosis of Diabetic Retinopathy and other methods that address this problem (But, they have some drawbacks like being accurate for small set of input data). This paper proposes the use of Artificial Neural Network, thereby classifying the diabetic retinopathy with the use of large input dataset (containing textual data regarding digital color fundus images).

Keywords : Diabetic Retinopathy; Artificial Neural Network; Classification; Backpropagation Algorithm.