Face recognition-based attendance systems have rapidly evolved as efficient solutions for automating attendance in educational and professional settings. Traditional methods- like roll calls and RFID systems-often face challenges such as inaccuracy, time consumption, and proxy attendance issues [1]. This research presents a face recognition-based system that integrates computer vision and deep learning to ensure precise and automated attendance tracking. It captures live images, extracts facial features, and verifies identity by comparing them to a pre-stored database. The system's methodology includes image acquisition, preprocessing, feature extraction using Convolutional Neural Networks (CNNs), and classification through deep learning models [2]. Its design aims to improve accuracy, reduce manual dependency, and enhance security. Experimental results demonstrate high recognition accuracy and a low false positive rate. With such potential, this system offers a transformative step in automating attendance, with a focus on security, reliability, and real-time operation. The study also discusses its benefits, limitations, and areas for future development.