Facial Recognition Based Attendance Monitoring System

Abstract

Proper monitoring of regular attendance is a strenuous as well as the cumbersome process in manual mode of operation. However, an automated computerized system can be designed for managing attendance utilizing several features of biometrics. The intervention of deep convolutional neural networks (CNNs) has simplified the process of face recognition. Maneuvering the promising results of CNN in terms of accuracy, a modified framework for attendance supervising based on the face recognition approach is proposed in the current manuscript. The facial recognition apparatus can acknowledge a similar human face from any digital image or video frame relying on an existing database of known faces. It operates by revealing and quantifying the features of the faces of an input image. The proposed framework can be used to verify users through ID verification services. The model is developed based on state-of-the-art approaches like CNN cascade for face detection and face embedding. The motivation of the work is to implement benchmark deep learning approaches in facial recognition tasks for real-life applications. In the recent era, facial recognition systems are used in all smart devices including mobiles, laptops, and robotics. The proposed recognition model can be used as a stand-alone system or may be incorporated in some other model for an automated monitoring process. © 2022, Springer Nature Switzerland AG.