Online Attendance Management System Based on Face Recognition Using CNN

Abstract

Due to the growing trend of online classes, there is a pressing need to create an efficient system that can keep track of the students’ regular presence in these lectures. The traditional method of manual calculation of attendance proves to be ineffective and time-consuming. Hence, this problem can be addressed by building a system which will perform the task of marking the attendance of students by matching their faces in the multiple frames of an online class with their respective images present in the database. In this paper, face detection and recognition is being done on a video given as input to our program. Multiple faces are detected and recognised simultaneously in a class lecture. Face detection and recognition application is implemented using an open source computer vision called OpenCV. The paper doesn’t venture into real time application though it has a future in real time detection. The essential algorithms that have been extensively used are Convolution Neural Network and VGG16 architecture along with Haar features. Moreover, significant changes are to be integrated in order to bring an upheaval in the major image analysis modules such that the framework incorporates accuracy and robustness even when other variations on poses are imposed. Our framework has been evolved to detect and recognise faces in fixed time periods and mark the student’s attendance according to the average value of the faces detected and recognised within those fixed time periods such that the online attendance system can’t be evaded or cheated.