Local Binary Pattern Histogram for Face Recognition in Student Attendance System

Abstract

Student attendance record has an important role in the educational process. Universitas Bhayangkara Jakarta Raya, as a case study, uses attendance record as the factor for final grade calculation. Many attendance recording systems were developed using biometrics, e.g. face recognition, iris recognition, and fingerprint recognition. In this study, face recognition was proposed since the face cannot be duplicated and can eliminate fraud committed by students. In addition, this contactless method could minimize the risk of COVID-19 spread with some additional treatments. The local binary pattern (LBP) was proposed in this study. This method has the ability to describe the texture and shape of an image by dividing the image into small portions of feature extraction. The result showed that the proposed system can identify students with 86% accuracy.