Cataract Detection in Retinal Fundus Image Using Gray Level Co-occurrence Matrix and K-Nearest Neighbor

DOI

10.2991/aer.k.211215.049How to use a DOI?

Keywords

Cataract; Fundus image; GLCM; KNN

Abstract

Cataract is one of the visual impairments that can lead to blindness if not detected and treated early. Cataract detection still takes a long time and is very objective based on the decision of the ophthalmologist. This is one of the reasons for conducting an automatic screening process based on fundus image analysis. This study was made as decision support for an ophthalmologist in determining whether someone has cataracts or not. There are three main stages in this research, namely preprocessing, feature extraction, and classification. Preprocessing perform by converting the image to grayscale and changing the image size so that the image is easier to process. The second stage is feature extraction by applying Gray Level Co-occurrence Matrix to extract contrast, correlation, energy, and homogeneity features. And the last stage is classification using k-nearest neighbors based on the features that have been obtained from the previous stage. The highest accuracy results obtained are 80% with k = 5, which indicates the proposed method can detect cataracts well.

Copyright

© 2021 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article under the CC BY-NC license.

Download article (PDF)

TY  - CONF
AU  - Nahya Nur
AU  - Sugiarto Cokrowibowo
AU  - Rosalina Konde
PY  - 2021
DA  - 2021/12/16
TI  - Cataract Detection in Retinal Fundus Image Using Gray Level Co-occurrence Matrix and K-Nearest Neighbor
BT  - Proceedings of the International Joint Conference on Science and Engineering 2021 (IJCSE 2021)
PB  - Atlantis Press
SP  - 268
EP  - 271
SN  - 2352-5401
UR  - https://doi.org/10.2991/aer.k.211215.049
DO  - 10.2991/aer.k.211215.049
ID  - Nur2021
ER  -