Article icon
Original research

Glaucoma diagnosis based on colour and spatial features using kernel SVM

* Corresponding author

[email protected]


The main aim of the paper is to develop an early detection system for glaucoma classification using the fundus images. By reviewing the various glaucoma image classification schemes, suitable features and supervised approaches are identified. An automated Computer Aided Diagnosis (CAD) system is developed for glaucoma based on soft computing techniques. It consists of three stages. The Region Of Interest (ROI) is selected in the first stage that comprises of Optic Disc (OD) region only. It is selected automatically based on the on the green channel's highest intensity. In the second stage, features such as colour and Local Binary patterns (LBP) are extracted. In the final stage, classification of fundus image is achieved by employing supervised learning of Support Vector Machine (SVM) classifier for classifying the fundus images into either normal or glaucomatous. The evaluation of the CAD system on four public databases; ORIGA, RIM-ONE, DRISHTI-GS, and HRF show that LBP gives promising results than the conventional colour features.


Anisha Rebinth, S. Mohan Kumar. Glaucoma diagnosis based on colour and spatial features using kernel SVM. Cardiometry; Issue 22; May 2022; p.508-515; DOI: 10.18137/cardiometry.2022.22.508515; Available from:


Glaucoma,  Fundus image classification,  Support vector machine,  Radial basis function kernel,  Local binary pattern,  Colour features
Download PDF
Cardiometry in Telegram
Current issue
Cardiometry's library
Founders of Cardiometry
Video about Cardiometry
Our partners