Automatic Detection of Microaneurysms in digital fundus images using LRE

Diabetic retinopathy is a complication of diabetes and a leading cause of blindness in the world. It occurs when diabetes damages the tiny blood vessels inside the retina. The main two types of diabetic retinopathy the first are non-proliferate diabetes retinopathy (NPDR) and second are proliferate diabetes retinopathy (PDR). Images analysis by trained individuals, which can be a very costly and time consuming task due to the large diabetic population. The increasing number of DR cases world-wide. Therefore, demands to the development of an automated detection system for reduce the work load of ophthalmologists in diagnosis the disease. This research proposed is developed computer based system for the automatically detection of diabetic retinopathy in the fundus images using Support vector classification (SVM) algorithm. The proposed methodology, using DIARETDB1 in which have total 89 images, achieves an accuracy of 95.38%, sensitivity of 94 % and a specificity of 94.7%.