부산대학교 도서관

In recent years, technologies related to Facial Recognition have undergone a remarkable upgradation in the domain of commerce as well as security. This paper presents an automated real-time attendance management system (AMS) using face recognition technique to reduce the human dependency and thereby saving the time. A modified local binary pattern histogram (MLBPH) algorithm based on calculation of based on pixel neighborhood gray median for extracting the significant features of the human face. More specifically, the facial landmarks are extracted to provide a completely unique result using MLBPH histogram. Further, the histogram of the input image is compared with database histogram using the classifier in the classification step. The human face matched with the database is used to mark attendance in the laboratory. The experiments reported a precision and recall of 97% and 95% respectively. This kind of biometric system is a real-time attendance system processing the human faces using simple and fast algorithms having higher accuracy can be deployed in schools.