Design and Implementation of an AI-Based Facial Recognition System for Automated Employee Attendance and Temporal Logging

Abstract

In today's digital environment, secure authentication is crucial in workplaces or educational institutions, as conventional attendance methods like manually operated registers as well as card-based systems are frequently inefficient, prone to errors, and susceptible to proxy attendance and data tampering. Despite the prevalent usage of biometric methods such as fingerprint and card authentication, they have constraints regarding efficiency, scalability, & user convenience. Facial recognition, as an non-contact and unobtrusive biometric method, offers a more safe and efficient option for identification verification. Many current solutions depend on rudimentary image processing and traditional machine learning techniques, leading to poor performance and restricted real-time application, while also failing to effectively integrate temporal recording. This study introduces the creation and execution of an AI-driven facial recognition system for automated staff attendance and time tracking. The suggested system employs sophisticated machine learning as well as computer vision methodologies to identify & identify faces during real time, while precisely documenting enter and exit timestamps. By integrating effective feature extraction & one-shot learning methodologies, the system guarantees dependable identification despite restricted training data. This method reduces manual involvement, deters proxy participation, and improves data integrity. Experimental findings demonstrate that the suggested system attains enhanced accuracy, accelerated processing, and superior adaptability relative to traditional attendance methods, rendering it a viable and scalable alternative for contemporary labor management.