Enhanced Nature Inspired-Support Vector Machine for Glaucoma Detection

Abstract

Glaucoma is a progressive eye disease that can lead to blindness if left untreated. Early detection is crucial to prevent vision loss, but current manual scanning methods are expensive, time-consuming, and require specialized expertise. This study presents a novel approach to Glaucoma detection using the Enhanced Grey Wolf Optimized Support Vector Machine (EGWO-SVM) method. The proposed method involves preprocessing steps such as removing image noise using the adaptive median filter (AMF) and feature extraction using the previously processed speeded-up robust feature (SURF), histogram of oriented gradients (HOG), and Global features. The enhanced Grey Wolf Optimization (GWO) technique is then employed with SVM for classification. To evaluate the proposed method, we used the online retinal images for glaucoma analysis (ORIGA) database, and it achieved high accuracy, sensitivity, and specificity rates of 94%, 92%, and 92%, respectively. The results demonstrate that the proposed method outperforms other current algorithms in detecting the presence or absence of Glaucoma. This study provides a novel and effective approach to Glaucoma detection that can potentially improve the detection process and outcomes.