Automatic Attendance Monitoring System Using LBPH and HAAR Algorithm

Abstract

Every office and organization must have an attendance monitoring system. Every institution has a standard attendance policy that requires the professor or assistant to report the student's name and attendance for each and every session. An automatic attendance monitoring approach will be suggested to replace this human process. Face spotting, an image processing tool, and face identification techniques are used in the research project that is being suggested. This method assists in turning video frames into numbers so that the human profile may be quickly recognized for attendance monitoring. The image captured from the video should be compared with the data saved with the date and time, which will be automatically stored in the memory storage, before a recognized attendance database is formed. The Viola-Jones Face Detection Technique, also known as the HAAR cascade algorithm, and the Local Binary Pattern Histogram (LBPH) algorithm were used in the development of the proposed automatic face recognition attendance monitoring system. Their combined features are used for attendance monitoring. The human face is first captured using the HAAR cascade technique, and then the LBPH algorithm is utilized to save the distinctive traits of each human face. During the face identification procedure, a predetermined user ID is retrieved from the algorithm data. This will produce the student's attendance data for their presence. The image processing system's data will need to be kept up to date and stored daily. The implementation of an automatic attendance tracking system will benefit from the suggested strategy. Anaconda software is used to implement and analyse the suggested attendance tracking system.