Application of Deep Learning on Student Attendance Checking in Virtual Classroom

Due to the situation of the COVID-19 outbreak, the importance of both virtual and hybrid conferences has unexpectedly increased, especially for the education sector. Additionally, the virtual classroom is the only method to make the education system grow while the COVID-19 outbreak situation is currently spreading. However, class attendance checking is a time-wasting problem for various online classes, which have more than 50 students. This research aims to help the course instructor by adapting the use of intelligent technologies in order to save the time that has been spent on the class attendance checking method. The deep learning techniques together with automatic screen-capturing mechanisms have successfully been designed and developed with Python, Flask, Sqlite, Html, CSS, and Javascript. Therefore, our proposed approach for attendance checking can automatically check the attendance of the enrolled students that belong to that particular class. In addition, this research uses front-face photos to train a deep learning model and deal with face recognition and image analytics for the student attendance checking methods. Therefore, the highlight of the system is the ability to take attendance automatically and continuously throughout the learning period. As a result, the use of our proposed system efficiently saved the attendance checking time and the proposed deep learning model has practically achieved acceptable accuracy at 91.77.