AI-Based Smart Attendance System with Face Recognition and QR Code

Abstract

Attendance management is an essential task in educational institutions and organizations for monitoring participation and maintaining records. Traditional attendance systems are often manual, time-consuming, and prone to errors such as proxy attendance and inaccurate record keeping. To address these challenges, this paper presents an AI-Based Smart Attendance System with Face Recognition and QR Code Technology that automates the attendance process while improving accuracy, efficiency, and security. The proposed system integrates Artificial Intelligence (AI), computer vision, and QR code technology to provide a reliable attendance management solution. Face recognition is implemented using deep learning and image processing techniques to identify individuals in real time through a camera. The system captures facial features, compares them with stored datasets, and automatically marks attendance for authenticated users. In addition, a QR code-based attendance module is incorporated as an alternative verification method, enabling users to scan unique QR codes for attendance registration when facial recognition is unavailable or affected by environmental conditions.

Introduction

This study presents an AI-based smart attendance system that automates attendance tracking using face recognition and QR code authentication. Traditional methods like manual registers, RFID, and fingerprint systems are limited by errors, proxy attendance, hygiene concerns, or security issues, motivating the need for a more reliable solution.

The proposed system uses Artificial Intelligence and Computer Vision to identify individuals through facial recognition while also generating and scanning unique QR codes for each user as a secondary verification method. During registration, student details and facial images are stored in a database, and a CNN model is trained after preprocessing the images to extract facial features. This enables accurate real-time recognition from live camera feeds.

When marking attendance, the system first recognizes the face and then verifies identity through QR code scanning. Once both checks are successful, attendance details such as ID, time, and date are automatically stored in a centralized database without duplication.

Conclusion

The AI-Based Smart Attendance System with Face Recognition and QR Code Authentication provides an efficient, secure, and automated solution for attendance management. The system successfully integrates Artificial Intelligence, Computer Vision, Deep Learning, and QR code technology to eliminate the limitations of traditional attendance methods, such as manual effort, human errors, and proxy attendance. The proposed system accurately identifies individuals using a CNN-based face recognition model and verifies their identity through QR code authentication. This dual-verification mechanism enhances security and ensures that attendance is recorded only for authorized users. The automated attendance marking process reduces administrative workload, saves time, and improves the overall efficiency of attendance management. Experimental results demonstrate that the system achieves high recognition accuracy and reliable performance in real-time environments. The attendance records are stored securely in a centralized database, allowing easy retrieval, monitoring, and report generation. The system also prevents duplicate entries and provides faculty members with detailed attendance reports for effective decision-making. Overall, the developed attendance system offers a practical and scalable solution for educational institutions and organizations seeking a modern attendance management approach. By combining face recognition and QR code technologies, the system ensures accurate attendance tracking, improved security, and enhanced operational efficiency. Future enhancements may include cloud-based deployment, mobile application integration, and advanced deep learning models to further improve system performance and accessibility.

References

[1] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 511–518, 2001. [2] G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, “Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments,” University of Massachusetts Amherst, Technical Report 07-49, 2007. [3] F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A unified embedding for face recognition and clustering,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815–823, 2015. [4] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems (NIPS), vol. 25, pp. 1097–1105, 2012. [5] D. E. King, “Dlib-ML: A machine learning toolkit,” Journal of Machine Learning Research, vol. 10, pp. 1755–1758, 2009. [6] G. Bradski, “The OpenCV Library,” Dr. Dobb’s Journal of Software Tools, vol. 25, no. 11, pp. 120–126, 2000.

Copyright

Copyright © 2026 Shrishail ., Vinodkumar , Dr. Savitha Patil. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.