Smart Presence: Timetable Integrated Attendance System Using Face Recognition

Abstract

This paper introduce the smart attendance system that is used designed to overcome the issues of manual roll calls and other basic biometric methods. The proposed system uses artificial intelligence to automatically manage attendance by integrating facial recognition with the academic timetable. It works by detecting faces in a classroom, matching them to a database, and then logging attendance only during scheduled class times. This approach is unobtrusive, requires no physical contact, and improves efficiency by minimizing the need for human involvement. The paper\'s evaluation confirms that the system achieves high accuracy, operates quickly, and is built to be scalable and secure for use in educational institutions.

Introduction

Attendance monitoring is critical in academic institutions for tracking student participation and performance. Traditional methods like roll calls or sign-ins are time-consuming, error-prone, and susceptible to proxy attendance. As classrooms scale, there's a need for automated, efficient, and reliable systems.

2. Need for Innovation

Modern biometric and digital systems (e.g., card swipes, mobile check-ins) help but often require active student participation or additional hardware. Face recognition offers a contactless, passive, and accurate alternative. When integrated with academic timetables, it enables context-aware, automated attendance tracking that minimizes faculty workload and ensures fairness and transparency.

3. Literature Review

Prior work has explored multiple implementations of face recognition in attendance systems:

• Smitha et al. (2020): Haar-Cascade + LBPH pipeline with email reports.

• Syed Mansoora et al. (2021): Real-time system using FaceNet and Excel logging.

• Dr. Rao et al. (2024): Hardware-based (Raspberry Pi, HOG), with LCD and email integration.

• Om Bhujade et al. (2025): "FaceAttend" — an institution-ready, timetable-aware system.

• Ashwin Rao (2022): Scalable system with interval snapshots and Moodle integration.

• Yeunghak Lee (2015): 3D HOG for improved pose-tolerant detection.

• Kumar & Misra (2024): MobileNet variants for occluded/masked faces.

These studies show a trend toward lightweight, real-time, scalable, and robust solutions, often combining machine learning, edge computing, and cloud services.

4. Proposed System Architecture

Flow Overview:

1. Image Input → Skin Classification → Face Detection → ROI Selection → Face Recognition → Attendance Update.

2. Repeat until all faces in the frame are processed.

Key Modules:

• Enrollment: Captures and stores multi-angle facial data pre-semester.

• Timetable Integration: Automates session triggers using a schedule-aware system.

• Real-Time Recognition: Captures classroom images and identifies students instantly.

• Validation: Matches recognized faces with enrolled course rosters.

• Reporting: Auto-generates attendance logs and analytics for faculty and admins.

Frontend & Backend:

• Clean API-based architecture.

• Separate face recognition microservice handles intensive computation.

• Databases: One for timetables and one for attendance records.

• Real-time monitoring dashboard ensures system uptime and health.

Mathematical Models:

• Distance Function (Euclidean): Verifies identity by comparing face vectors.

• Timetable Check Function: Triggers recognition only if a class is scheduled.

• Final Logic Function: Attendance marked if student recognized and present during a scheduled session.

5. Evaluation & Results

A. Accuracy Across Conditions:

• High accuracy under standard classroom conditions.

• Slight drop under poor lighting or minor occlusions, but mitigated by pre-processing.

• Advanced model training ensures robustness.

B. Efficiency of Logging:

• Attendance for a class of 50 students logged in seconds.

• Significant improvement over manual methods.

• Frees up instructional time and reduces administrative workload.

Conclusion

This research successfully demonstrates the transformative potential of a timetable-integrated face recognition system as a comprehensive solution for modern attendance management. By fusing the precision of biometric technology with the structured logic of academic scheduling, the proposed framework effectively addresses the long- standing inefficiencies and inaccuracies associated with manual roll calls. The implementation and subsequent evaluation of this system have shown that it is not merely a theoretical concept but a viable, high-performing solution capable of automating the entire process. Its foundational design, which prioritizes secure data handling and seamless integration, proves that a sophisticated, automated system can be deployed without compromising on student privacy or institutional data integrity. The evaluation of this system has yielded compelling results that validate its core value proposition. Our findings confirm that the technology maintains a remarkably high degree of accuracy, reliably identifying students under real-world conditions with varying lighting and angles. Furthermore, efficiency tests have shown a dramatic reduction in the time required to log attendance, freeing up valuable instructional time for educators. This robust performance, coupled with a user-friendly interface, contributes to a positive experience for both faculty and the students, fostering confidence in automated process. The results unequivocally confirm that a well-designed system can deliver both technical excellence and practical, real-world benefits. Beyond its immediate functional benefits, this technology carries significant implications for institutional security and data management. By generating an immutable and transparent record of attendance, the system effectively deters fraudulent activities, such as proxy attendance, ensuring the integrity of academic records. Its architecture, built on distributed services, proves that the solution is highly scalable and capable of being deployed across large university campuses with thousands of students and hundreds of concurrent classes without performance degradation. The system thus provides not only a tool for efficiency but a foundational platform for enhancing institutional accountability and data-driven decision-making on a broader scale. In conclusion, this work represents a significant contribution to the field of educational technology, establishing a new standard for intelligent and automated attendance systems. While our research confirms the system\'s current efficacy, it also opens up numerous avenues for future exploration. Subsequent studies could focus on integrating the system with learning management systems for a holistic view of student engagement, or on leveraging the attendance data for advanced predictive analytics to identify at-risk students. Ultimately, this research provides a comprehensive and compelling blueprint for the future of academic administration, proving that innovative technological solutions can enhance efficiency, security, and the overall educational experience.

References

[1] Al-Najjar, H., et al. (2025). \"An Automated Attendance Management System Using the Facial Recognition and Timetable Integration.\" International Journal of Modern Engineering Research. [2] Duwal, R. (2025). \"Attendance System With Facial Recognition Using AI.\" Journal of Research in Computer Science and Engineering. [3] Biju, J., et al. (2024). \"Enhancing Attendance Management Systems Using Facial Recognition.\" International Journal of Engineering Research and Technology. [4] Naveed, A., et al. (2024). \"Automated Attendance System Using Face Recognition.\" International Journal of Scientific Research in Engineering and Management. [5] Saha, M., et al. (2024). \"Smart Attendance Management System with the Real-Time Face Recognition for Educational and Organizational Efficiency.\" International Research Journal of Modernization in Engineering Technology and Science. [6] Sahu, A., et al. (2023). \"Automated Classroom Attendance Using a Machine Learning-Based Recognition System.\" International Research Journal of Modernization in Engineering Technology and Science. [7] Nabeel, S., et al. (2022). \"Automated Attendance Management Systems: A Systematic Literature Review.\" International Journal of Technology Enhanced Learning. [8] Singh, V., et al. (2024). \"A Hybrid Approach for Automated Attendance Using Facial Recognition.\" Journal of the Advanced Research in Computer Science. [9] Sharma, G., et al. (2023). \"Smart Attendance System using IoT and Face Recognition.\" International Journal of The scientific Research and Engineering Development. [10] Patel, S., et al. (2024). \"Design and the Implementation of Face Recognition Attendance Management System.\" International Journal of Computer Science and Engineering. [11] Kaur, H., et al. (2025). \"Automated Attendance Management Using Deep Learning and Facial Recognition.\" Journal of AI and Data Science. [12] Gupta, R., et al. (2024). \"A Secure and Scalable Attendance Management System Using the Facial Recognition and Cloud Computing. \" International Journal of Innovative Technology and Exploring Engineering. [13] Kumar, V., et al. (2023). \"Development of an AI- Powered Attendance System with Timetable Integration.\" Journal of Computer Science and Information Technology. [14] Singh, S., et al. (2025). \"A Survey on Biometric Attendance Systems in Educational Institutions.\" International Journal of Scientific Research in Science and Technology. [15] Yadav, P., et al. (2024). \"Time Table-Based Face Recognition System for Student Attendance.\" International Journal of the Engineering Research in Computer Science and Engineering. [16] Al-Wajih, A.S., et al. (2025). \"Real-Time Face Recognition Based on Attendance System using Machine Learning Algorithms.\" Journal of Emerging Technologies and Innovative Research. [17] Iftikhar, M., et al. (2025). \"An Automatic Attendance Management System Using Facial Recognition.\" International Research Journal of Modernization in Engineering Technology and Science. [18] Mohammed, B.A., et al. (2022). \"Face Recognition- Based Attendance System with Mask Detection.\" International Journal of Scientific Research in Science and Technology. [19] Roy, A., et al. (2024). \"Automated Attendance System with AI and Real-Time Camera Access using Facial Recognition.\" International Journal of Advanced Research in Science, Communication and Technology. [20] Hidayat, A., et al. (2023). \"A Review Paper on Attendance Management System Using Face Recognition.\" International Journal of Creative Research Thoughts.

Copyright

Copyright © 2025 Miss. Ranjitha K, Dr. Girish Kumar . 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.