ISSN: 0973-7510

E-ISSN: 2581-690X

R. Vijayalakshmi1 and S. Selvarajan2
1Department of Computer Science and Engineering, Muthayammal Engineering College,
Tamilnadu, India.
2Muthayammal College of Engineering, Rasipuram-637408, Tamilnadu, India.
J Pure Appl Microbiol. 2015;9(Spl. Edn. Aug.):65-70
© The Author(s). 2015
Received: 10/02/2015 | Accepted: 01/05/2015 | Published: 31/08/2015
Abstract

Retinal images can be classified by an improved Computer Aided Clinical and Decision Support System using Neural Network is presented in this paper. The Optic Disc features such as thickness of vessels (blood, main and branch), diameter of vein, cup area have been extracted by applying a variety of neural network techniques for classification purpose. By using SVM classifier, percentage of False Acceptance rate and False Rejection rate are noticed to be very less when compared with different classifiers. The proposed system has established 98.45% accuracy. The load of experts can be decreased considerably using automatic disease recognition system by preventing the referrals to those cases which requires instant attention. The proposed system decreases the time utilization and applies additional efforts on screening patients’ diseases turn out to be normal.

Keywords

Median Filtering, Abnormality detection, diabetic retinopathy, SVM

Article Metrics

Article View: 1000

Share This Article

© The Author(s) 2015. Open Access. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License which permits unrestricted use, sharing, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.