This study aims to overcome the limitations of fingerprint biometric authentication in computer-based examinations by introducing a robust face recognition system. The research targets key challenges such as administrative overhead, prolonged authentication times, and issues with false positives and negatives. By leveraging advanced technologies like Multi-Task Cascaded Convolutional Neural Network (MTCNN) for precise facial detection and FaceNet for efficient facial feature embedding, the developed system achieves substantial improvements across critical metrics. The evaluation metrics consistently report high ratings: accuracy 90%, speed 92%, ease of use 86%, robustness to variations 94%, security 92%, and privacy 90%. Evaluation of the system shows its superiority over traditional fingerprint methods. It demonstrates notably higher accuracy, efficiency, user-friendliness, adaptability to diverse conditions, and enhanced levels of security and privacy. These advancements position the face recognition system as a compelling alternative for enhancing the authentication processes in computer-based examinations. Keywords: FaceNet, Multi-Task Cascaded Convolutional Neural Network, Face Recognition, Security, Face, Fingerprint Detection. Sulaimon O.O., Olabiyisi, S.O. & Ismaila, W.O. (2024): Development of a Face Recognition System for Authentication in Computer-Based Examinations: A Comparison with Fingerprint Verification. Journal of Advances in Mathematical & Computational Science. Vol. 12, No. 2. Pp 117-128. Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V12N2P8