Decision support system for the glaucoma using Gabor transformation.

•Normal and glaucoma classes are classified using digital fundus images.•Gabor transformation and principal component analysis are used to extract the features.•Bhattacharyya space algorithm, t-test, Wilcoxon test, Receiver Operating Curve (ROC), and entropy method are used for feature ranking.•Support Vector Machine (SVM) classifier gives the highest average accuracy of 93.10%, sensitivity of 89.75% and specificity of 96.20% using 23 features.•A Glaucoma Risk Index (GRI) is developed using selected principal components to classify the two classes using just one number.