Extraction of Blood Vascular Network for Development of an Automated Diabetic Retinopathy Screening System

Segmentation of vascular structures of retina for implementation of Clinical diabetic retinopathy decision making systems is presented in this paper. As retinal vascular structure is with thin blood vessels, prediction accuracy is highly dependent upon the segmentation and preprocessing schemes. Complex GSZ shock filters have been used for noise suppression and edge enhancement. Binarization algorithms are used to achieve the segmentation of vascular structures of the retina. It has been observed that the combination of shock filter and Binarization provides better segmentation results compared to morphological and region growing methods.