Automatic Detection of Exudates in Diabetic Retinopathy Images

Automatic Detection of Exudates in Diabetic Retinopathy Images

Abstract— According to the increasing consumption of sugar materials in human life and growing trend of the machine life, the prevalence of diabetes is on the rise. It is observed all patients with this disease mostly suffer from decrease or loss their vision. For the automatic diagnosis of diabetic retinopathy (DR) and determination of a diabetic eye from a healthy eye, we need to extract several features from retinopathy images. There are various< Final Year Projects > possible characteristics can be extracted from the retina photography images, hence it is significant to discover the most effective features for detection of diabetic retinopathy. In this study the Gaussian filter is used to enhance images and separate vessels with a high brightness intensity distribution. Next, wavelets transform is used to extract vessels. After that according to some criteria such as vessels density, the location of optic disc was determined. Then after optic disc extraction, exudates regions were determined. Finally we classified the images with a boosting classifier. With utilizing the boosting algorithm, the suggested system can have a power classifier. It is generated by a combination of some weak and simple learners. Hence, this approach can reduce the complication and time consuming operation.