Colour Retinal Image Enhancement based on Domain Knowledge Gopal Datt Joshi, Jayanthi Sivaswamy Centre for Visual Information Technology IIIT-Hyderabad, India gopal@research.iiit.ac.in, jsivaswamy@iiit.ac.in Abstract Retinal images are widely used to manually or automat- ically detect and diagnose many diseases. Due to the com- plex imaging setup, there is a large luminosity and con- trast variability within and across images. Here, we use the knowledge of the imaging geometry and propose an enhancement method for colour retinal images, with a fo- cus on contrast improvement with no introduction of arti- facts. The method uses non-uniform sampling to estimate the degradation and derive a correction factor from a single plane. We also propose a scheme for applying the derived correction factor to enhance all the colour planes of a given image. The proposed enhancement method has been tested on a publicly available dataset [8]. Results show marked improvement over existing methods. 1. Introduction Among the many uses of retinal images are in the early detection and diagnosis of many eye diseases such as dia- betic retinopathy (DR) and age-related macular degenera- tion (AMD). Automated analysis techniques for retinal im- ages has been an important area of research of late for de- veloping screening programmes [8]. In retinal images, vas- cular topography, dark and bright pathology (subtle or oth- erwise) are mainly of interest. A good quality of image is essential for a reliable diagnosis performed either manually or automatically. Therefore, improvement of image quality is a fundamental problem in retinal image analysis. Retinal images are acquired with a digital fundus cam- era, which captures the illumination reflected from the reti- nal surface. Despite the controlled conditions under which imaging takes place, there are many patient-dependent as- pects which are difficult to control. Thus, most retinal im- ages suffer from non-uniform illumination. Some of the contributing factors are: (a) The curved surface of the retina. Consequently, all retinal regions cannot be illuminated uni- formly; (b) Imaging requires a dilated pupil. The degree of Figure 1. A retinal image with uneven illumi- nation and contrast. dilation is highly variable across patients; (c) Unexpected movements of the patients eye. The bright flash-light makes the patient move his/her eye away from the view of the camera involuntarily; (d) Presence of other diseases such as cataract which can block the light reaching the retina. These factors result in images having a large luminosity and contrast variability within and across images. Hence, for a reliable diagnosis, whether manual or automated, an image normalization step is necessary. A sample of typical retinal image is shown in figure 1 af- fected by non-uniform illumination. In can be observed that luminosity and contrast distribution is not uniform across the image. Such variations affect the detection, for instance, of important objects such as microaneurysms (MA) which are of interest in early diagnosis of DR. These appear as a tiny red dots in a colour retinal images as highlighted in im- ages shown in figure 2. The sample MA regions and the blood vessels (red lines/curves) also occur with varying lo- cal contrast across images. A normalisation step is hence Sixth Indian Conference on Computer Vision, Graphics & Image Processing 978-0-7695-3476-3/08 $25.00 © 2008 IEEE DOI 10.1109/ICVGIP.2008.70 591 Sixth Indian Conference on Computer Vision, Graphics & Image Processing 978-0-7695-3476-3/08 $25.00 © 2008 IEEE DOI 10.1109/ICVGIP.2008.70 591 Sixth Indian Conference on Computer Vision, Graphics & Image Processing 978-0-7695-3476-3/08 $25.00 © 2008 IEEE DOI 10.1109/ICVGIP.2008.70 591