Among the most promising biometric technologies for non-contact, real-time person identification, facial recognition is quickly rising to the top. Because of how efficient and convenient it is, its use has expanded greatly in fields including security systems, access control, and surveillance. Manual roll calls and fingerprint-based systems are two examples of the outdated attendance techniques used in academic institutions. These alternatives are typically seen to be obtrusive, time-consuming, and vulnerable to proxy attendance. This study suggests a face recognition-based AI attendance system to automate and simplify the attendance process in educational environments, which would solve these constraints. A pair of well-known algorithms for real-time image processing the Haar Cascade Classifier for face identification and the Local Binary Patterns Histograms (LBPH) method for face recognition are used by the suggested system. The solution is built using OpenCV, Python, and a graphical user interface made using Tkinter. Administrative tasks such as student record management, face sample generation, recognition model training, and attendance logging are all accessible via the interface. A safe login mechanism is built into the system to ensure that only authorized users may access it. It performed consistently well, recognized objects quickly, and accurately under typical indoor lighting circumstances. By automating the process, decreasing human error, and doing away with the possibility of proxy attendance, this system provides a viable and effective substitute for conventional attendance tracking methods. It is well-suited for use in educational settings including classrooms and training canters due to its modular and expandable architecture.
Anand et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: