AUTOMATED ATTENDANCE MANAGEMENT SYSTEM USING FACIAL RECOGNITION TECHNIQUES

Abstract

This investigation introduces an automated method for monitoring the attendance of students or employees through the use of facial recognition technology, which improves accuracy, speed, and safety. Traditional methods, including biometric technologies and human roll calls, are error-prone, burdensome, and susceptible to fraudulent attendance. The proposed method employs computer vision and deep learning algorithms to identify and recognize individuals in real time using a camera. Upon the identification of a match within a database of known images, attendance is automatically documented. Convolutional Neural Networks (CNNs) are frequently employed by the system for the purposes of face detection, feature extraction, and classification. It ensures that individuals are not obligated to take any action, reduces administrative duties, and provides a dependable, contactless response, which is particularly advantageous in regions that are impacted by a pandemic. The attendance records can be stored online for swift access and analysis. The research demonstrates that attendance systems are more reliable, scalable, and efficient when facial recognition technology is implemented.