Thresholding approaches for extracting optic disc in digital fundus image

Abstract

In this paper, thresholding approaches are analyzed to locate the optic disc in colour fundus image. The approaches used in the system are the well known Otsu thresholding and iterative thresholding technique. As green plane in the fundus image provides best contrast, it is used to extract the Region of Interest (ROI). Before extracting ROI, it is necessary to de-noise the image. Median filtering is applied for this purpose. Then ROI is extracted based on the intensity value of the optic disc. To locate the optic disc region Otsu and iterative techniques are applied. Results show that the location of optic disc identified by iterative thresholding technique is better than the Otsu method.