The retina, which directly connects to the brain, is crucial in ophthalmology, and analyzing retinal fundus images is vital. However, these images often have issues like degradation from varied imaging qualities or disease-related distortions such as Glaucoma, Retinoblastoma, Diabetic Retinopathy, Myopia, and Macular Edema. Glaucoma causes permanent blindness worldwide, so catching it early is crucial. This work introduces a new method using the YOLOv8 algorithm, a cutting-edge technology that detects objects. We aim to use YOLOv8 to find signs of glaucoma quickly and accurately in eye images, allowing for early diagnosis. We trained the algorithm on a varied set of images, including normal and glaucomatous ones, making it adaptable to different types of disease. Our tests show that the YOLOv8 algorithm is effective at spotting specific signs of glaucoma, like changes in the optic disc and thinning of the neuroretina rim. It performs well compared to other methods, proving its potential for automated screening in medical settings. In summary, integrating the YOLOv8 algorithm into glaucoma detection processes seems promising, providing a swift and precise way to identify early signs of the disease in eye images. This research contributes to developing efficient automated systems for early detection and treatment of glaucoma, which can ultimately enhance patient outcomes and decrease the impact of blindness. The hope is that our work helps in the ongoing efforts to fight glaucoma, making it easier to identify and treat the disease early, leading to better outcomes for patients and reducing the overall burden of blindness globally.