Paper Contents
Abstract
Glaucoma, a progressive optic neuropathy and major cause of irreversible blindness, necessitates timely and accurate detection for effective management. This paper explores implementation research on glaucoma detection frameworks that combine Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs), with a specific focus on the integration of attention mechanisms. This hybrid approach aims to leverage the automated feature extraction of CNNs and the classification capabilities of SVMs, while attention mechanisms enhance focus on critical retinal regions to improve diagnostic accuracy and interpretability. The report provides a detailed analysis of methodologies, a performance comparison against CNN-only approaches, an examination of system architectures, and an overview of publicly available implementations, offering a comprehensive understanding of current research trends in this vital area of medical image analysis.
Copyright
Copyright © 2025 Pragati Chandane. This is an open access article distributed under the Creative Commons Attribution License.
