International Journal of Computer Techniques – Volume 2 Issue 1, 2015 ISSN: 2394 -2231 http://www.ijctjournal.org Page 1 Detection of Optic Disc in Retina Using Digital Image Processing Vijaya Patil, M. Phil, Vaishali Kumbhakarna, M. Phil, Dr. Seema Kawathekar, Asst. Prof, Department of Computer Science, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad ----------------------------------------------------********************************************--------------------------------------------------------- Abstract: The retinal fundus image is widely used in the diagnosis and treatment of various eye diseases such as diabetic retinopathy and glaucoma. We propose a method to automatically detect the optic disc in fundus images of the retina. The method includes edge detection using the canny operators and detection of circles using the Hough transform method. In the proposed method, the images are collected from the DIARETDB0 and DIARETDB1 databases which are publicly available on the Internet. Keywords: Diabetic retinopathy, glaucoma, canny, Hough transforms ---------------------------------------------------********************************************----------------------------------------------------------- .I. INTRODUCTION Retinal Image Analysis is a key element in detecting retinopathies in patients. Diabetic Retinopathy is one of the most common diabetic eye conditions which cause blindness induced by alterations in the blood vessels of the retina [7]. The general image of human eye is shown in Fig. 1. Fig.1: Anatomy of eye Diabetic Retinopathy (DR) is a retinal disease derived from complications caused by the abnormally high glucose level in blood produced by diabetes mellitus. Nowadays, DR is the leading ophthalmic pathological cause of blindness among people of working age in developed countries. Automatic detection of optic disc from retinal images is very essential and crucial for expert ophthalmologists to diagnose diseases. Localisation of the retinal optic disk has been attempted by several researchers recently [2]. Typically the optic disc looks like an orange-pink donut with a pale centre, see Fig. 2. Fig. 2: Retina A. Suero [6] proposed a methodology for OD location in fundus images. Input images are intensity images (I channel of the HSI color space), resized to have a retinal diameter of 300 pixels. shade-correction method for homogenizing the background as well as a set of morphological opening and closing operations for enhancing bright structures, are applied to find a pixel within OD. R. Radha [9] Proposed a method for the Retinal image analysis through efficient detection of exudates which recognizes the retinat to be normal or abnormal. The contrast image is enhanced by curvelet transform. Hence, morphology operators are applied to the enhanced image in RESEARCH ARTICLE OPEN ACCESS