Library Attendance System using YOLOv5 Faces Recognition

Recognizing a large number of faces at the same time is an algorithmic and computational challenge. The integration of a facial recognition system with an existing automation system in a library is also a big challenge because of the many sub-systems that operate in it. The aim is to develop a prototype of a library attendance system to assist library management related to facial recognition of users who visit the library. This study uses image processing focuses on object detection using the YOLOv5 algorithm. The library attendance system integrates 3 sub-systems: API service, face recognition using YOLOv5, and visitor identification system. The results obtained are that the library attendance system can function properly, can read the API service, and display information on the results of face detection therefore the system can be used by the existing library automation system.