Automated Student Attendance System with Real-Time SMS Notification

Abstract

Attendance management plays a crucial role in academic institutions, yet traditional methods often face challenges such as time consumption, human errors, and the possibility of proxy attendance. Inaccurate attendance tracking can lead to poor monitoring of student participation, lack of transparency, and delayed communication with parents. To address these issues, this project presents an Automated Student Attendance System with Real-Time SMS Notification, a smart web-based solution designed to improve accuracy and efficiency in attendance management. The proposed system captures student images through a webcam and uses face recognition techniques to automatically identify individuals by comparing them with a pre-registered database. Based on this identification, attendance is recorded instantly without manual intervention. In addition, the system sends real-time SMS notifications to parents regarding their child’s attendance status, ensuring timely updates and improved communication. The application is developed using modern technologies such as Python, OpenCV, Dlib, Flask, and MySQL to ensure efficient processing and reliable data management. Its simple and user-friendly interface makes it easy to use in classroom environments with minimal technical effort. By integrating intelligent face recognition with real-time notification services, the system aims to enhance transparency, reduce manual workload, and improve overall attendance monitoring. Overall, the project demonstrates how automation and communication technologies can modernize academic systems and contribute to better student management and institutional efficiency.

Introduction

The Automated Student Attendance System with Real-Time SMS Notification is a web-based solution designed to improve attendance management in educational institutions through face recognition technology and instant parent notifications. Traditional attendance methods such as manual roll calls are time-consuming, error-prone, and vulnerable to proxy attendance. The proposed system addresses these challenges by automating attendance recording and enhancing communication between institutions and parents.

The system captures live video through a webcam, detects and recognizes student faces using OpenCV, Dlib, and facial encoding techniques, and automatically marks attendance by comparing detected faces with a pre-registered student database. Once attendance is recorded, real-time SMS notifications are sent to parents through services such as Twilio, providing immediate updates on their child's attendance status. Attendance records are securely stored in a MySQL database for future tracking and monitoring.

The architecture consists of several integrated modules, including User Interface, Student Registration, Face Detection, Face Recognition, Attendance Management, Database Management, Notification, and Reporting & Monitoring modules. The frontend provides an easy-to-use interface, while the backend, developed using Python and Flask, manages recognition, attendance processing, and database operations.

Compared to previous attendance systems, the proposed solution offers greater automation, improved recognition accuracy, reduced manual effort, prevention of proxy attendance, and enhanced parental involvement through instant notifications. The system was tested in a classroom environment and demonstrated reliable face detection, accurate attendance marking, secure data management, and prompt SMS delivery.

Conclusion

This paper presented the design and implementation of an Automated Student Attendance System with Real-Time SMS Notification aimed at improving efficient attendance management. The integration of face recognition technology, real-time notification services, and structured data handling enables accurate and reliable attendance tracking. By combining Python-based backend processing with a responsive web interface developed using Flask, HTML5, CSS, and JavaScript, the system ensures smooth and user-friendly operation for academic environments. The recognition framework evaluates facial features and compares them with stored data to generate precise identification and automatic attendance recording along with notification delivery. The modular and scalable architecture allows easy updates to student records and system functionalities, ensuring adaptability to different institutional requirements. Although the system currently operates using face recognition libraries and rule-based matching, future enhancements can include deep learning-based models, integration with cloud platforms, and improved real-time processing capabilities. Further improvements may also involve mobile application support and enhanced security features for better data protection. Overall, the proposed framework demonstrates strong potential to modernize attendance systems, improve monitoring efficiency, and support transparent academic management through intelligent digital solutions

References

[1] S. Sharma et al., “Face Recognition-based Attendance System using OpenCV,” Int. Journal of Computer Applications, vol. 182, 2022. [2] R. Patel and K. Mehta, “Automated Attendance Management System using Face Recognition,” Int. Journal of Engineering Research & Technology, 2023. [3] “Face Recognition Attendance System using Python,” ResearchGate, 2023 — This system uses image processing and facial encoding techniques to automate attendance marking. [4] “Smart Attendance System using Deep Learning,” ResearchGate, 2024 — Focus on improving accuracy using CNN-based face recognition models. [5] “AI-based Attendance Monitoring System with Face Recognition,” ResearchGate, 2025. [6] A. Kumar, “Student Attendance System using OpenCV and Dlib,” Hindustan Univ. Project, 2022. [7] P. Singh and R. Verma, “Real-Time Face Recognition System for Smart Attendance,” Int. Journal of Advanced Computer Science, 2024. [8] S. Reddy et al., “Web-Based Attendance System using Flask and MySQL,” Sci. Rep. / Nature, 2025. [9] M. Khan, “Face Recognition System using Machine Learning Techniques,” Sustain. Comput.: Informatics and Systems, 2024. [10] H. Ali et al., “Automated Student Monitoring using Face Recognition and IoT,” Sci. Rep., 2025. [11] N. Gupta, “Evaluation of Face Recognition Models for Attendance Systems,” Information, vol. 16, 2025. [12] T. Joseph, “Face Recognition Techniques: A Survey,” Comput. Vision and Image Processing Journal, vol. 175, 2020. [13] K. Nair and S. Das, “Smart Attendance System using Deep Learning Algorithms,” Curr. Computer Science Research, 2022. [14] Face Recognition Model Reference — Deep learning-based facial recognition models for real-time identification systems. [15] “Smart Attendance System with SMS Notification using Twilio API,” Curr. Engineering Applications, 2023. [16] Y. Zhao, J. Lin, and X. Wang, “A Real-Time Face Recognition System for Attendance using Deep Learning,” IEEE Access, vol. 9, pp. 145632–145641, 2021.

Copyright

Copyright © 2026 Ms. P. Nava Bhanu , M. Aswini, N. Sahithi, V. Keerthana. 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.