Detection of exudates for diabetic retinopathy using wavelet transform

Abstract

Retinopathy is the one of the disorder caused in human retina because of diabetic disease. Exudates are the one prime sign of diabetes presence. This paper presents detection of exudates from color retina image using discrete wavelet transform and feature extraction method for classification of human retina as normal or diabetic. Blood vessels are separated using mathematical morphology that helps for extraction of optic disc and exudates. Exudates information is used for classification and the method applied in this paper on color retina images provide good results which can be compared with previous used methods.