Authors : Olugbenga Oloniyo; Folowo Damilare Samuel; Adeniranye Fredrick

Volume/Issue : Volume 10 - 2025, Issue 8 - August

Google Scholar : https://tinyurl.com/yc72v8yx

Scribd : https://tinyurl.com/2tz6a4ma

DOI : https://doi.org/10.38124/ijisrt/25aug720

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Accurate and tamper-proof attendance monitoring is a challenge in educational, corporate and administrative settings. Existing systems that are solely dependent on manual entry, RFID card or biometric authentication with single- mode are often vulnerable to manipulation, impersonation and inconsistency of data. This study presents the design and implementation of a multimodal attendance system that integrates radio frequency identification (RFID), face recognition, fingerprint biometric and GSM-based SMS notifications to improve reliability, safety and accountability. The proposed system uses an ESP32 microcontroller to coordinate multiple hardware modules, including an RC522 RFID reader, an AS608 fingerprint sensor, an ESP32-CAM for facial recognition, and a SIM800L GSM module for mobile communication. Upon RFID approval, the system performs sequential fingerprints and face recognition, and ensures identity confirmation through at least two biometric modalities. Successful verification triggers real-time logging, timestamp and an SMS notification to a designated recipient. Experimental validation was performed using a test population, and the results show improved accuracy, low false acceptance/rejection rate and real-time responses. The system supports local data storage and provides scalability for integration with cloud -based platforms. This research contributes to the development of secure, efficient and user-centric attendance management systems through the deployment of multimodal biometric technologies.

Keywords : Attendance System, Biometric Authentication, Face Recognition, Fingerprint Sensor, RFID.

References :

1. Olanipekun, A. A., & Boyinbode, O. K. (2015). A RFID based automatic attendance system in educational institutions of Nigeria. International Journal of Smart Home, 9(12), 65–74. https://doi.org/10.14257/ijsh.2015.9.12.07
2. Riaz, I., Ali, A. N., & Ibrahim, H. (2024). Loss of fingerprint features and recognition failure due to physiological factors: A literature survey. Multimedia Tools and Applications, 83, 87153–87178. https://link.springer.com/article/10.1007/s11042-024-19848-8
3. Henniger, O., Scheuermann, D., & Kniess, T. (2021). On security evaluation of fingerprint recognition systems. Fraunhofer Institute for Secure Information Technology. https://www.nist.gov/system/files/document
4. Palanichamy, N. (2024). Occlusion-aware facial expression recognition: A deep learning approach. Multimedia Tools and Applications, 83, 32895–32921. https://link.springer.com/article/10.1007/s11042-023-17013-1
5. Kavi Priya, K., & Deepa, M. I. (2024). Enhancing occlusion handling in face recognition: A performance analysis of deep learning models. International Journal of Research Publication and Reviews, 5(10), 831–837. https://ijrpr.com/uploads/V5ISSUE10/IJRPR
6. Singh, L. K., Khanna, M., & Garg, H. (2020). Multimodal biometric based on fusion of ridge features with minutiae features and face features. International Journal of Information System Modeling and Design, 11(1), 37–57. https://doi.org/10.4018/IJISMD.2020010103
7. Kausar, H., Ikhar, A., Akhtar, F., Padole, G., & Kshirsagar, P. (2024). AI-based automated biometric sensor & RFID entry system with Arduino. Journal of the Institution of Industrial Engineers India, 1(May), 128–134. http://www.journal-iiie-india.com/1_may_24/128_online_may.pdf