Monitoring and presence are two things that are interconnected in learning and attendance in class. For attendance lists or attendance there are still many shortcomings and can be cheated, supervision in learning is also one of the keys to improving the quality of learning, especially during exams. Face recognition application is one of the solutions to this problem, in this study the authors built a monitoring application and presence in
learning. For face detection and recognition using the Local Binary Patterns Histograms method and also the OpenCV library as an eye or a camera for image capture. Image
captured in realtime. In this application the attendance list will come from a length of 1 learning hour (SKS) which will automatically attendance when the time is sufficient. This study also measures several conditions as one that affects the accuracy of face detection and recognition. The conditions include : light intensity, distance, accessories and face position. The test results show the detection accuracy rate is 100% with certain conditions, while the face recognition accuracy rate gets 92.3% and the average
recognition time is 0.802 seconds.

Monitoring and presence are two things that are interconnected in learning and attendance in class. For attendance lists or attendance there are still many shortcomings and can be cheated, supervision in learning is also one of the keys to improving the quality of learning, especially during exams. Face recognition application is one of the solutions to this problem, in this study the authors built a monitoring application and presence in learning. For face detection and recognition using the Local Binary Patterns Histograms method and also the OpenCV library as an eye or a camera for image capture. Image captured in realtime. In this application the attendance list will come from a length of 1 learning hour (SKS) which will automatically attendance when the time is sufficient. This
study also measures several conditions as one that affects the accuracy of face detection and recognition. The conditions include : light intensity, distance, accessories and face position. The test results show the detection accuracy rate is 100% with certain conditions, while the face recognition accuracy rate gets 92.3% and the average
recognition time is 0.802 seconds.