Glaucoma is a leading cause of irreversible blindness worldwide, often progressing without noticeable symptoms until significant vision loss occurs. Early detection is critical to prevent permanent damage, but conventional screening methods are time-consuming and require expert interpretation. In recent years, deep learning has emerged as a powerful tool in medical image analysis, offering promising solutions for automated and accurate glaucoma detection. This paper explores the application of deep learning techniques, particularly convolutional neural networks (CNNs), to detect glaucoma from retinal fundus images. A curated dataset of labeled fundus images is used to train and evaluate the model, achieving high accuracy in distinguishing glaucomatous eyes from normal ones. The study highlights the potential of deep learning to enhance the efficiency and accessibility of glaucoma screening, paving the way for real-time clinical decision support systems. Future directions include improving model generalizability across diverse populations and integrating multimodal data to further boost diagnostic performance.