An Automated System for Colored Retinal Image Background and Noise Segmentation Anam Tariq * and M. Usman Akram † Department of Software Engineering * , Department of Computer Engineering † Fatima Jinnah Women University * College of Electrical and Mechanical Engineering † National University of Sciences and Technology Pakistan Email: anam.tariq86@gmail.com * , usmakram@gmail.com † Abstract—Retinal images are used for the automated diagnosis of diabetic retinopathy. The retinal image quality must be improved for the detection of features and abnormalities and for this purpose segmentation of retinal images is vital. In this paper, we present a novel automated approach for segmentation of colored retinal images. Our segmentation technique smoothes and strengthens images by separating the background and noisy area from the overall image thus resulting in retinal image enhancement and lower processing time. It contains coarse segmentation and fine segmentation. Standard retinal images databases Diaretdb0 and Diaretdb1 are used to test the validation of our segmentation technique. Experimental results indicate our approach is effective and can get higher segmentation accuracy. I. I NTRODUCTION Diabetes affects almost every one out of ten persons, and has associated complications such as vision loss, heart failure and stroke. Diabetic eye disease refers to a group of eye problems that people with diabetes may face as a complication of diabetes. Patients with diabetes are more likely to develop eye problems such as cataracts and glaucoma, but the disease´ s affect on the retina is the main threat to vision [1]. Complication of diabetes, causing abnormalities in the retina and in the worst case blindness or severe vision loss, is called Diabetic Retinopathy [1]. There are no such symptoms in the early stages of diabetes but the number and severity mostly increase as the time passes. Most patients develop diabetic changes in the retina after approximately 20 years [2]. The common symptoms of diabetic retinopathy are blurred vision (this is often linked to blood sugar levels), floaters and flashes, and sudden loss of vision [2]. To determine if a person suffers from diabetic retinopathy, retinal image is used. Performing the mass screening of dia- betes patients will result in a large number of images, that need to be examined. The cost of manual examination is prohibiting the implementation of screening on a large scale. A possible solution could be the development of an automated screening system for retinal images [1]. Such a system should be able to distinguish between affected retinal images and normal retinal images. This will significantly reduce the workload for the ophthalmologists as they have to examine only those images diagnosed by the system as possibly abnormal [3]. A tool which can be used to assist in the diagnosis of diabetic retinopathy should automatically detect all retinal image features such as optic disk, fovea and blood vessel [5], [6], [7] and all abnormalities in retinal image such as microaneurysms [4], [8], [9], hard exudates and soft exudates [10], [11], hemorrhages, and edema [4]. Retinal images are characterized by uneven illumination, blurry and noisy areas. The center region of a retinal image is usually highly illuminated while the noise increases closer to the edge of the retina [17]. So, Illumination equalization and noise removal are required to enhance the image quality . Fig. 1 shows three different quality retinal images taken from standard diabetic retinopathy databases, diaretdb0 and diaretdb1 [12]. Fig. 1. (a) Uneven illuminated retinal image; (b) Blurred retinal image; (c) Noisy retinal image. Prior to the detection of retinal image features and abnor- malities, segmentation of retinal image must be done for the re- liable detection of abnormalities. The purpose of segmentation is to remove the noisy area and unwanted regions from retinal image. It is particularly significant for the reliable extraction of features and abnormalities. Feature extraction and abnormality detection algorithms give poor results in the presence of noisy background area. Fig. 2 shows the input color retinal image and the segmented retinal image. The aim of segmentation is to increase the quality of an image by reducing the amount of noise appearing in the image and highlighting features that are used in image segmentation. Two typical techniques used in segmentation are filtering and contrast enhancing. Standard contrast stretching techniques have been applied by [4], [13] for segmentation and noise reduction. In [14], [15] and [16] the local contrast enhance- 2010 IEEE Symposium on Industrial Electronics and Applications (ISIEA 2010), October 3-5, 2010, Penang, Malaysia 978-1-4244-7647-3/10/$26.00 ©2010 IEEE 423