This document presents research on using machine learning algorithms to detect glaucoma from fundus images. The researchers extracted various texture and intensity features from fundus images using methods like gray level co-occurrence matrix, histogram of oriented gradients, wavelet transforms, and shearlet transforms. They used feature selection to reduce the number of features before classifying the images as normal or glaucomatous using support vector machines and K-nearest neighbors algorithms. The best accuracy of 97.5% was achieved using wavelet features. The researchers evaluated the classification performance using metrics like accuracy, sensitivity, specificity, and predictive values to assess the ability of the extracted features to detect glaucoma.