Title: Detection of fovea region in retinal images using optimisation-based modified FCM and ARMD disease classification with SVM

Authors: T. Vandarkuzhali; C.S. Ravichandran

Addresses: Department of Electrical and Electronics Engineering, Hindusthan College of Engineering and Technology, Coimbatore, India ' Department of EEE, Sri Ramakrishna Engineering College, Coimbatore, India

Abstract: The underlying motive resting with the current investigation is invested in designing a superior recognition system for locating the fovea region from the retinal image by significantly steering clear of the roadblocks encountered at present. The significant scheme streams through three specific processes particularly, blood-vessel segmentation, optic-disc detection, fovea detection and ARMD disease classification. In the initial stage, the retinal images are enhanced with the help of AHE approach and then segmented by adaptive-watershed technique. The successive stage opens up with recognition of optic-disc by means of MRG system. And, in the last stage, the fovea region is effectively spotted with the help of OBMFCM technique. Along with the fovea-region segmentation, analysis is made for the classification of dry/wet ARMD with SVM classifier. The record-breaking technique is performed in the platform of MATLAB2014 and its charismatic upshots are assessed and contrasted with those of the parallel fovea recognition approach.

Keywords: OBMFCM; age-related macular degeneration; ARMD; adaptive histogram equalisation; AHE; modified region growing; MRG; support vector machine; SVM.

DOI: 10.1504/IJBET.2020.104678

International Journal of Biomedical Engineering and Technology, 2020 Vol.32 No.1, pp.83 - 107

Received: 14 Dec 2016
Accepted: 01 Mar 2017

Published online: 28 Jan 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article