Detection of the optic disc in images of the retina using the Hough transform

We propose a method to locate automatically the optic disc (OD) in fundus images of the retina. Based on the properties of the OD, our proposed method includes edge detection using the Sobel or the Canny method, and detection of circles using the Hough transform. The Hough transform assists in the detection of the center and radius of a circle that approximates the margin of the OD. Based on the feature that the OD is one of the bright areas in a fundus image, potential circles detected by the Hough transform are analyzed using intensity. Forty images of the retina from the DRIVE database were used to evaluate the performance of the proposed method. The success rates including both good and acceptable detections were 92.50% using the Sobel operators and 80% using the Canny edge detector.