Early Detection of Diabetic Retinopathy in Fundus Images Using GLCM and SVM
S Deva Kumar1, Gnaneswara Rao Nitta2
1S Deva Kumar, Department of Computer Science and Engineering, VFSTR deemed to be University, Vadlamudi, Guntur (Andhra Pradesh), India.
2Dr. Gnaneswara Rao Nitta, Professor, Department of Computer Science and Engineering, VFSTR deemed to be University, Vadlamudi, Guntur (Andhra Pradesh), India.
Manuscript received on 12 February 2019 | Revised Manuscript received on 02 March 2019 | Manuscript Published on 08 June 2019 | PP: 17-20 | Volume-7 Issue-5S4, February 2019 | Retrieval Number: E10040275S419/19©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: Diabetes enhances the risk of destruction of blood vessels that pumps blood vessels that pumps blood to the retina an aliment known as Diabetic Retinopathy (DR). In diabetic retinopathy appearing of Microaneurysms is the first clinical sign. Hence, identification of Microaneurysms becomes a major problem solving task, in which fundus images plays a very important role. If this is detected in early stage, it is very much useful to the ophthalmologist to treat the patients in avoiding the blindness of the patients by their treatment. In this paper, we are proposing an automatic method for detection of Microaneurysms from Diabetic Retinopathy fundus photographs. For detecting simple and efficient methods are used. The methods are Preprocessing using CLAHE (Contrast Limited Adaptive Histogram Equalization), Blood Vessels (BV) extraction by using Kirsch’s operator followed by feature extraction using Gray Level Co-occurrence Matrix (GLCM) detection of MAs and Classification using SVM. On evaluating the results, the proposed method got better performance than the existing method.
Keywords: Diabetic Retinopathy, Microaneurysms, Glcm, Svm Classifier.
Scope of the Article: Image Security