Attendance System using Face Recognition

Abstract

In this digital era, face recognition system performs an important role in every sector. Face recognition is one of the most commonly used biometrics in day today life. It can be used for security, authentication, identification, verification and many more advantages as such. In spite of having low accuracy when compared to iris recognition and fingerprint recognition, it is being widely used due to its contactless and non-invasive process being advanced. Furthermore, face recognition system can be used for attendance marking in schools, colleges and offices, etc. This system sets a goal of fulfilment of building a class attendance system which uses the concept of face recognition as existing manual attendance system is time consuming and very difficult to maintain. And there may be high chances of proxy attendance from students. Thus, the need for this system increases satisfying these criteria. This system consists of four phases- database creation, face detection, face preprocessing, face recognition and attendance updation. Once the Face detection and recognition is performed, the image is converted to black and white format using Haar-Cascade classifier and then further converted to values using Local Binary Pattern Histogram algorithm respectively. Faces are usually detected and recognized from live streaming image of the classroom. Attendance will be mailed to the respective faculty at the end of the session.