Glaucoma is a leading cause of irreversible blindness, making early and accurate diagnosis essential for effective treatment. Traditional diagnostic methods, reliant on manual assessment, can be time-consuming and prone to errors. To address these limitations, automated systems leveraging deep learning and image processing techniques have emerged as promising solutions. This paper surveys recent advancements in glaucoma detection using retinal fundus images, focusing on models such as convolutional neural networks (CNNs), vision transformers, and hybrid approaches that integrate imaging data with clinical biomarkers. Additionally, we examine key trends, including transfer learning, feature extraction, and attention mechanisms, which have significantly improved diagnostic accuracy. While deep learning-based approaches have demonstrated remarkable progress, challenges such as data scarcity, model interpretability, and clinical validation remain. By synthesizing findings from recent literature, this study highlights the potential of AI-driven solutions in ophthalmology while identifying gaps that need to be addressed for reliable real-world implementation.