Red Lesions Identification of Retina for Diabetic Patients

Abstract

The automatic identification of retinal lesions in fundus images is crucial. In this paper, the approach used for identification of microaneurysms and hemorrhages in fundus images is appropriate. By using this technique, the features of changing shape for the identification of red lesions in the fundus images are effective in which segmentation is not necessary. While image flooding, shape features are evolved and characterized between red lesions and vessel segments.