Enhancing Face Recognition Accuracy through Integration of YOLO v8 and Deep Learning: A Custom Recognition Model Approach

Student attendance and being present during lectures plays a very important role in the value of the lesson and understanding of each student. There are a number of methods to record the attendance of the students such as signature on paper, QR code, RFID method and finally model based system. The most used method is signature of students even though it is mostly used it suffers from unethical behavior by some students and students forgetting to register their attendance. This research will develop a system to improve attendance registration accuracy by integrating it with custom recognition model. The class will be installed with a device that consists of a microcontroller and camera. The system will take an image of the class and send it to the database to be analyzed and then after recognizing the faces each face will be registered followed by the date and time it has been detected. All data will be stored in a database. The database can be accessed by the lecturers at the end of the class to review the attendance of students without the need to waste time on manually registering it.