This document summarizes a research paper that proposes a method for detecting and classifying stages of non-proliferative diabetic retinopathy (NPDR) in retinal images. The method uses morphological operations to detect three retinal features - blood vessels, microaneurysms, and hard exudates. These features are extracted and the distribution in four retinal quadrants is used as input to an SVM classifier to classify images as normal, mild NPDR, moderate NPDR, or severe NPDR. The method was tested on 337 retinal images and achieved an average accuracy of 95%, sensitivity of 96.08% and specificity of 97.92% for classification. The results demonstrate the method can successfully classify NPDR stages, though classification