Published Paper Details:

Diabetic-retinopathy is the leading cause of blindness in the working age population. So far the most effective treatment for these eye diseases is early detection through regular screenings. To decrease the cost of such screenings, we employ methods image processing techniques to automatically detect the presence of abnormalities in the retinal images obtained during the screenings. In this paper, we used two methods. First approach is that detection of lesions using minimum distance discriminat (MDD) algorithm with brightness adjustment procedure. Second method is detection of blood vessels using Krisch's method. Experimental results indicate that we are able to achieve 100% accuracy in terms of identifying all the retinal images with exudates while maintaining a 75% accuracy in correctly classifying the truly normal retinal images as normal and also detects the affected blood vessels in the retinal image . This translates to a huge amount of savings in terms of the number of retinal images that need to be manually reviewed by the ophthalmologists.