Performance Evaluation of Different Methods for Detection of Hemorrhage Using Fundus Images

Image processing of a fundus image is performed for the early recognition of diabetic retinopathy. Diabetic retinopathy classified in two stages. First is non-proliferative which includes microanearism and when blood vessels are leak and it comes into proliferative stage which is called hemorrhage. In this paper I discussed about detection of hemorrhage in diabetic retinopathy. extraction of hemorrhages using template matching with templates of various shapes has not been reported.Microanuarisem are early sign of diabetic retinopathy Detection of hemorrhage may help the clinician in the diagnosis of diabetic retinopathy and might be a useful tool for early detection of diabetic retinopathy progression especially in the telemedicine. Diabetic retinopathy is a serious complication of diabetes mellitus and a major cause of blindness worldwide. Signs of diabetic retinopathy include red lesions such as micro aneurysms (MA), intraregional hemorrhages, and bright lesions, such as exudates and cotton wool spots. So early detection and proper treatment can prevent our eyes from blindness. In this paper I discussed hybrid method and brightness correction method for detection of hemorrhage in diabetic retinopathy. There was using various shape of template for detection of hemorrhage. Second method I applied in this study it was brightness correction and clahe method for detection. For recognize exact shape of hemorrhage region growing segmentation was used. Diabetic retinopathy is the most common cause of blindness in the working population of the United States. Early diagnosis and timely treatment have been preventing visual loss and blindness in patients with diabetes.