Detection of Lesions in Color Fundus Images for Diabetic Retinopathy Grading
Chitra Raju I1, Lizy Abraham2
1Chitra Raju I, Department of Electronics and Communication, LBS Institute of Science and Technology for Women, Thiruvananthapuram (Kerala), India.
2Dr. Lizy Abraham, Department of Electronics and Communication, LBS Institute of Science and Technology for Women, Thiruvananthapuram (Kerala), India.
Manuscript received on 15 August 2015 | Revised Manuscript received on 25 August 2015 | Manuscript Published on 30 August 2015 | PP: 155-160 | Volume-4 Issue-6, August 2015 | Retrieval Number: F4200084615/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Advancement in technology has its impact in many areas especially in the field of medicine. Analysis of medical images have great significance in non-invasive treatment and clinical studies. In the context of computer aided diagnosis of diabetic retinopathy, a new algorithm for the detection of lesions is presented and discussed. The regions where these lesions are present determines the severity of diabetic retinopathy. Thus, the detection of these lesions plays a vital role in computer aided diagnosis. Detection of fovea is indispensable for this approach. Fovea is detected by means of morphological operations. The method has been tested on publicly available databases and the results are better than the conventional approaches.
Keywords: Diabetic Retinopathy (DR), Exudates, Fovea, Hemorrhages
Scope of the Article: Image Processing