Glaucoma is a serious eye disease that leads to irreversible vision loss if not detected at an early stage. It is primarily caused by increased intraocular pressure, which damages the optic nerve. Early diagnosis plays a crucial role in preventing permanent blindness; however, traditional diagnostic methods are time-consuming and require expert ophthalmologists. This project presents an automated glaucoma detection system using digital image processing techniques applied to retinal fundus images. The proposed system focuses on extracting key features such as the optic disc, optic cup, and calculating the cup-to-disc ratio (CDR), which is a significant indicator of glaucoma. Image preprocessing techniques including noise removal, contrast enhancement, and segmentation are employed to improve accuracy. The extracted features are then analyzed to classify the eye as normal or glaucomatous. The system aims to provide a cost-effective, efficient, and reliable method for early glaucoma screening, thereby assisting ophthalmologists in diagnosis and reducing the risk of vision loss.