AI-BASED SMART OFFICE ENTRY AND COLLEGE ATTENDANCE SYSTEM USING FACE RECOGNITION

The attendance system in the college with the help of AI based smart office entry and face recognition is intelligent and feasible solution to improve the security and attendance management system. Through the integration of YOLO, which is used for face detection in real-time with CNN, face recognition takes place, making sure that the right people get recognized and their attendance recorded without any need for physical contact. This approach will help save on manual work and inaccuracies, and eliminate issues such as proxy attendance. Besides, this system makes the offices and colleges more secure as only the registered users can access to the offices. It can be further developed by optimizing the system for challenging scenarios such as low illumination, facial expression variations and faces covered by objects and/or masks. Future research directions may involve applying state-of-the-art deep learning architectures like Vision Transformers, along with developing lighter neural networks, for achieving high recognition rates in real-time. There are additional ways to enhance the system that can involve having multiple camera settings, visitor tracking and cloud-based attendance management systems for large businesses and schools. Also, the system can be connected to mobile applications, access control devices and smart building technologies via Internet of Things (IoT) to enable centralized management and efficient operation.

1.      Budiman, A., Yaputera, R. A., Achmad, S., & Kurniawan, A. (2023). Student attendance with face recognition (LBPH or CNN): Systematic literature review. Procedia Computer Science, 216, 31-38. 2.      Trigueros, D. S., Meng, L., & Hartnett, M. (2018). Face recognition: From traditional to deep learning methods. arXiv preprint arXiv:1811.00116. 3.      Rao, A. (2022, November). AttenFace: A real time attendance system using face recognition. In 2022 IEEE 6th Conference on Information and Communication Technology (CICT) (pp. 1-5). IEEE. 4.      Shriwastav, S., & Jain, D. C. (2016). A review on face recognition attendance system. The International Journal of Computer A publications (0975–8887), 143(8). 5.      Wang, C. Y., Bochkovskiy, A., & Liao, H. Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 7464-7475). 6.      Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. 7.      M. D. Kelly, “Visual identification of people by computer.,” tech. rep., STANFORD UNIV CALIF DEPT OF COMPUTER SCIENCE, 1970. 8.      T. KANADE, “Picture processing by computer complex and recognition of human faces,” PhD Thesis, Kyoto University, 1973. 9.       K. Delac and M. Grgic, “A survey of biometric recognition methods,” in 46th International Symposium Electronics in Marine, vol. 46, pp. 16– 18, 2004. 10.   U. Park, Y. Tong, and A. K. Jain, “Age-invariant face recognition,” IEEE transactions on pattern analysis and machine intelligence, vol. 32, no. 5, pp. 947–954, 2010.