YOLOv8- Enhanced Facial Recognition for One-Shot Learning Attendance System

Assessing student attendance is crucial in classrooms because it influences how well students perform. The integration of advanced image processing technology has streamlined the critical functions of our classroom attendance monitoring system. We proposed a method for student attendance control using face recognition with advanced one-shot learning to track student at-tendance efficiently. Our approach included employing YOLOv8, OpenCV, and face recognition frameworks for face detection and storage optimization by storing a single image per person. Our work achieved an accuracy of 97 % for 50 student's datasets using a webcam. This innovative method surpasses traditional training-testing methodologies, enhancing effectiveness while effectively addressing authentication and logistical challenges within atten-dance management systems.