<p>Glaucoma is a sight threatening eye disease caused by damage to the optic nerve, which can lead to irreversible vision loss if not treated promptly. Traditional methods of glaucoma detection rely on clinical assessments and manual interpretation of imaging data, which can be time-consuming and subject to variability. The integration of computer-based technologies has eased this task and assisted practitioners in the detection of the disease with improved accuracy, speed, and also early detection of the disease. This paper provides a comprehensive overview of the use of computers in glaucoma detection. Specifically, widely used image technologies for glaucoma diagnosis are presented, highlighting the importance of medical imaging in early detection and monitoring. Moreover, we gather and present a comprehensive compilation of over a 20 available image datasets specific to glaucoma research, facilitating future algorithm development and benchmarking efforts. We review recent advancements in computer-aided methods for glaucoma detection, categorizing them into four groups based on their underlying architectural paradigms. Each group is systematically evaluated, discussing the strengths and limitations of its approaches. Furthermore, a performance comparison of these methods is conducted, revealing the superior performance of deep learning for glaucoma detection. Finally, the paper discusses the future research directions and challenges for widespread deployment of CAD systems in primary health care facilities.</p>