Face Recognition Based Smart and Robust Attendance Monitoring using Deep CNN

Abstract

It is difficult for teachers to deal with student attendance during classes, whether online or offline since they do it by hand as they use their teaching time. To solve this problem, the smart and insightful attendance management system can be used. Authentication leads to the biggest impediment. The current structure uses biometric authentication, such as voice analysis and signature verification. The study suggested a system of attendance tracking built on facial recognition that can strengthen traditional biometric authentication. The architecture is a relationship between computers and humans and addresses a robust method of authentication. To identify a face, the system uses HOG and SVM and uses an existing database for labeling attendance. The experimental results show the device can automatically identify the faces recorded by the camera accurately and we can detect the face more precisely and efficiently with the use of the SVM classifier.