期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2011
卷号：2
期号：6
页码：2694-2699
出版社：TechScience Publications
摘要：Diabetic Retinopathy (DR), a common micro vascular disease observed in diabetics, is also a major cause of adult blindness across the globe. It results in observable changes in retina which may be cured, provided, if it is detected in the preliminary stage. However, the ocular images produced by fluorescent oscilloscope are often noisy and low in contrast making it seriously difficult for doctors to precisely detect the inherent abnormalities. In the present paper, we propose to use a regional contrast enhancement scheme, popularly known as Contrast Limited Adaptive Histogram Equalization (CLAHE) to aid the detection of retinal changes in DR imagery. CLAHE is an adaptive extension of Histogram Equalization followed by thresholding, which helps in dynamic preservation of the local contrast characteristics of an image. Following CLAHE, median filtering of DR images is carried in order to smoothen the background noise. Results of the proposed algorithm show a considerable improvement in the enhancement of DR image.ication.
