Automated Smart Attendance System with Face Recognition

Abstract

In this paper, the development of the smart attendance system with face recognition technology is presented. The proposed system is fully automated and does not require. The system has been implemented on a Raspberry Pi 4 Model B board using a USB webcam automatically detects and recognizes people in real-time and records their presence in a centralized database. The proposed system utilizes OpenCV and the concept of face recognition models like CNNs to guarantee proper recognition regardless of changes lighting conditions. When compared with the traditional method, this contactless technology has been found to result in a lower increase in errors and prohibits proxy attendance. Results for the experimental evaluation of the hardware prototype justify the following conclusions on the desirability and functionality an average face recognition accuracy of over 90% (95% in well-lit conditions, around 90% in low-lighting conditions) and average processing latency of approximately 1-2 seconds per recognition. The power consumption is restricted to a standard *5V/3A USB Power Supply, for continuous use*. The paper describes the hardware and software components \"Software design, methods of software testing, including unit and black box tests, and performance measurement.\" Lastly, the benefits of the system are highlighted, and future enhancements are touched upon.

Introduction

The text discusses the challenges of managing attendance in educational institutions and organizations and proposes an automated, efficient solution using face recognition technology. Traditional attendance methods—like roll calls, punch cards, and RFID—are time-consuming, prone to errors, and susceptible to proxy attendance. Modern computer vision-based systems, especially those using Convolutional Neural Networks (CNN) and deep learning, offer accurate, non-contact, and hygienic alternatives.

The proposed system uses a Raspberry Pi 4 Model B as the processing unit, coupled with a USB camera, a micro-SD card for storage, and a monitor for visualization. The system captures video frames, detects faces, and matches them with a pre-registered database to automatically log attendance with timestamps in a SQLite database. A user-friendly interface displays real-time attendance status.

Objectives of the system include:

1. Automating attendance marking through face recognition.

2. Improving accuracy and preventing proxy attendance.

3. Providing a non-contact, hygienic solution.

4. Centralizing and making attendance records easily retrievable.

5. Offering an efficient solution for schools, colleges, and offices.

Literature review highlights:

• Face is the most distinctive biometric feature for identification.

• Techniques like LBP (Local Binary Patterns), HOG, PCA, SVM, KNN, and CNN improve accuracy in face detection and recognition.

• Deep learning-based face recognition enhances system performance and prevents fake attendance.

• Touchless systems are especially relevant for health safety, e.g., during COVID-19.

• Automated systems reduce the burden on faculty and can scale for large populations.

System components and methodology:

• Raspberry Pi 4: Central processing unit running Python/OpenCV and machine learning libraries.

• USB Camera: Captures real-time video frames for face recognition.

• Micro-SD Card: Stores OS, code, datasets, and attendance logs.

• Monitor: For setup, debugging, and real-time monitoring.

• Hardware setup is compact, cost-effective, and capable of real-time operation, making it suitable for classrooms, offices, and institutions.

Conclusion

In this project, designed and implemented an autonomous attendance system with face recognition. The system efficiently detects and recognizes faces in real time, automatically marking attendance without any manual effort. Using OpenCV and Python-based facial recognition algorithms, the project provides an accurate, contactless, and intelligent attendance management solution. The system’s performance analysis demonstrates its high accuracy, reliability, and efficiency, making it suitable for practical applications in schools, colleges, offices, and other organizations. It simplifies attendance tracking, reduces human errors, and improves data handling through automation solutions.

References

[1] Preethi, K., & Vodithala, S. (2021, May). Automated smart attendance system using face recognition. In 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS) (pp. 1552-1555). IEEE. [2] Senthil, G. A., Geerthik, S., Karthikeyan, R., & Keerthana, G. (2024, June). Face Recognition based Automated Smart Attendance using Hybrid Machine Learning Algorithms and Computer Vision. In 2024 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC) (pp. 606-611). IEEE. [3] Thalluri, L. N., Babburu, K., Madam, A. K., Kumar, K. V. V., Ganesh, G. V., Rajasekhar, K., & Yaswanth, V. V. N. (2024). Automated face recognition system for smart attendance application using convolutional neural networks. International Journal of Intelligent Robotics and Applications, 8(1), 162-178. [4] Sawhney, S., Kacker, K., Jain, S., Singh, S. N., & Garg, R. (2019, January). Real-time smart attendance system using face recognition techniques. In 2019 9th international conference on cloud computing, data science & engineering (Confluence) (pp. 522-525). IEEE. [5] Patel, S., Kumar, P., Garg, S., & Kumar, R. (2018). Face Recognition based smart attendance system using IOT. International Journal of Computer Sciences and Engineering, 6(5), 871-877. [6] Al-Muhaidhri, G., & Hussain, J. (2019). Smart attendance system using face recognition. International Journal of Engineering Research and, 8, 10-17577.

Copyright

Copyright © 2026 Venugopal Karampuri, Dr. B. Sampath Kumar, Omkar Dhaygude, Sanket Atanure, Amisha Jamadar, Priyadarshini Birajadar, Saniya Nadaf, Babusha Shendage. 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.