Visual examination of eye structures like the optic disc (OD) allows precise detection of conditions such as glaucoma, diabetic retinopathy, and other abnormalities. Medical image processing, with a focus on ophthalmic imaging, plays a crucial role in the diagnosis and grading of retinal pathologies. In this chapter, an automated approach for OD localization in eye fundus images is introduced. The method involves a vessel diminishing stage utilizing the Optimized Top-Hat transformation, with parameter optimization performed by the RUNge Kutta metaheuristic optimizer (RUN). Subsequently, OD segmentation is carried out using the Minimum Cross-Entropy Thresholding-Harris Hawks Optimization (MCET-HHO) method, followed by centroid calculation and image cropping for final OD detection. The proposed method is assessed across three datasets, encompassing a variety of eye conditions and imaging settings. A numerical evaluation employing key performance metrics compares the calculated OD center coordinates and segmentations with manual expert marks, where accuracy values of 99.69% and 99.77% were achieved for normal and glaucomatous images, respectively. This methodology serves as a robust pre-processing tool for OD analysis, demonstrating great robustness in a wide range of fundus images.