ENHANCING CLASS ATTENDANCE WITH AI: A STUDENT FACE RECOGNITION SYSTEM USING OPENCV

Abstract

Background: With the rapid advancement of technology, there is an increasing need to incorporate these innovations into education, particularly in attendance tracking. Traditional methods, such as roll calls, are inefficient, error-prone, and unsuitable for large classes. Computer vision, a subset of artificial intelligence (AI), utilizes machine learning and neural networks to extract valuable information from digital images and videos, aiding in well-informed decision-making.
Methods: This study employs computer vision, a subset of AI, using the OpenCV library to develop a Student Facial Recognition system. The system captures and analyzes students' images during class sessions, automatically recording their attendance. Actual classroom experiments were conducted to evaluate the system's effectiveness and accuracy.
Results: The Student Facial Recognition system has demonstrated its value by achieving a 92% accuracy rate in identifying students, with an average processing time of 10 seconds per student. This level of efficiency and accuracy can significantly enhance the attendance tracking process in educational institutions.
Conclusion: In conclusion, the facial recognition system holds promise for improving attendance tracking, but it also raises significant data privacy and ethical concerns that require careful consideration. Despite these challenges, the system's potential to transform attendance tracking in education is reason for optimism. Future research should address these issues and explore the technology's broader potential in education.