Development of smart class attendance by using facial recognition

Adnan, Muhammad Syahrizzat (2020) Development of smart class attendance by using facial recognition. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

	Text (24 Pages) Development of smart class attendance by using facial recognition.pdf - Submitted Version Download (611kB)
	Text (Full Text) Development of smart class attendance by using facial recognition.pdf - Submitted Version Restricted to Repository staff only Download (2MB)

Abstract

Nowadays, attendance management of students using the conventional methods had been a challenge to a lecturers or teachers especially with a large number of students. It is not only a time-consuming task, but it can be a burden to the lecturers or teachers. Besides, due to the large number of students, there is always a possibility of proxies and fake attendance. Hence, several automated attendance systems are using biometric verification have been proposed. Facial recognition technology is one of the biometric methods and is widely used in the attendance management system. By using the facial recognition technique, issues such as proxies and fake attendance can be avoided and most importantly is timesaving. However, previously proposed systems have some drawbacks such as lightning of the images, noise from the camera, and the angle of student face that made the attendance management ineffective and inefficient. Therefore, this paper proposes high speed and accurate attendance management using facial recognition techniques. In this paper, Raspberry Pi 4, Pi camera and dlib’s algorithm are utilized as a microcontroller, camera and algorithm for facial recognition, respectively. During the attendance taking session, student’s face that captured by the camera is identified in the database. Once it has been identified, student’s attendance is recorded in the system. Then, an email is sent to student’s parent as a notification for their attendance in class. From the experimental results, the captured student’s face is successfully recognized, and attendance is successfully recorded in the system. Besides, time taken for parents received a notification email once attendance is recorded is about 3.8s if a total student in class is 30 students.

Actions (login required)

View Item