


Volume 20 No 20 (2022)
Download PDF
Severity Assessment of Glaucoma using Soft computing Techniques
H S Vijaya Kumar and M. A. Jayaram
Abstract
This paper elaborates the development of an automated system founded on approximate reasoning for the detection and
severity assessment of glaucoma, which is considered to be dreaded visual impairment. Around 100 glaucomatous images
selected after mining 180 such images formed inputs to the system. The automated systems for detection and severity
assessment namely BPNN aided system, and FIS based systems were developed. The pre-processing of images proved that
DBMF is the best among other filters experimented. As a testimony DBMF showed low value of MSE, high value of PSNR,
and high fidelity. The three input features namely CDR, annular space width between disc and cup, and percentage
constriction of annular space provided appropriate attributes for accurate damage assessment. The performance of FIS based
damages assessment system shows accuracy in the range of 80% - 85%. The system based on BPNN model with topology 3-
9-1 was found to be optimal. The system showed the classification accuracy in the range of 86% - 95% during testing stage
and 83% - 90% during validation stage.
Keywords
Glaucoma, Automated system, CDR, DBMF, BPNN, FIS, Accuracy
Copyright
Copyright © Neuroquantology
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.