Efficient Attendance Management System Based on Face Recognition

Abstract

Every education institution nowadays is concerned about student attendance and performance. In the current academic system, consistent class attendance of students plays a significant role in their performance, assessment, and quality monitoring. The traditional approach of taking attendance in several institutions is by calling the names of students one after the other or each student manually signs on the papers. In existing approaches, taking and tracking student’s attendance manually, losing attendance sheets, dishonesty of students, and high error scales are open challenges face by the faculties. It is a complex process, requires time, and causes manual paperwork. We proposed an efficient and robust approach for an attendance monitoring system using the face of a human. The proposed algorithm first detects and recognizes the student’s faces from videos or images. Second, mark the attendance using a neural network model and texture features. Experiments were conducted on the commercially available datasets. The proposed approach is compared with the traditional attendance marking system in terms of time and accuracy. Our approach resolves the state-of-the-art approach challenges and saves time to monitor the students.