Home / Current Issue / Paper 1719235
IoT-Based Smart Attendance System Using Android Camera Streaming and Deep Learning Face Recognition
Subject area: Science,Engineering and Technology · Area of research: IoT-Based Facial Recognition Systems
DOI: 10.64388/IREV9I12-1719235
Abstract
The growing demand for efficient, contactless, and automated attendance management in educational institutions has driven the development of intelligent systems that leverage Internet of Things (IoT) and artificial intelligence technologies. This paper presents the design and implementation of a Smart Attendance System that integrates an Android smart phone as a wireless IoT camera node, a Python-based deep learning service for real-time face recognition, and a full-stack web application for attendance management and analytics. The proposed system eliminates the limitations of traditional attendance methods such as manual roll calls, RFID cards, and fingerprint scanners by providing a completely contactless, hardware-minimal solution. The Android device streams live video over a local Wi-Fi network using the MJPEG protocol. A Python edge-computing service reads this stream using OpenCV, detects faces using Haar Cascade classifiers, and performs identity verification using the DeepFace library with the VGG-Face deep neural network model. Upon successful recognition, attendance records are automatically posted to a Node.js REST API and stored in a MongoDB database. The system features a React-based web dashboard for real-time monitoring, attendance logs, and R-powered statistical analytics including ARIMA-based forecasting and PDF report generation. Experimental results demonstrate that the system achieves reliable face recognition under standard indoor lighting conditions, marks attendance within seconds of recognition, and provides a scalable, cost-effective alternative to existing solutions. The system is built entirely on open-source technologies, requires no dedicated hardware beyond a standard Android smart phone and a laptop, and is deployable in any institution with a basic Wi-Fi infrastructure.
Keywords
MPEG, ARIMA, WIFI, VGG Face
References
[1] Ahonen, T., Hadid, A., & Pietikäinen, M. (2006). Face description with local binary patterns: Application to face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(12), 2037–2041.
[2] Babu, J. N. (2025). SMART WASTE IMAGE DETECTION. International Journal of Emerging Technologies and Innovative Research (JETIR), 12(12), e469–e472. ISSN: 2349-5162. http://www.jetir.org/papers/JETIR2512457.pdf
[3] Babu, J. N., et al. (2025). Traffic Violation Fine Tracker. International Journal of Emerging Technologies and Innovative Research (JETIR), 12(12), c608–c611. ISSN: 2349-5162. http://www.jetir.org/papers/JETIR2512268.pdf
[4] Babu, J. N., et al. (2025). AI-Enabled Forecasting and Isolation Forest-Based Detection of CBF Flow Anomalies in Secure Internet Architectures. Journal of Internet Services and Information Security, 15(3).
[5] Babu, J. N., et al. (2013). Indian License Plate Recognition System Based on Fuzzy Theory and BP Neural Network. International Journal of Electronics and Communication Technology (IJECT), 4(1). ISSN: 2230-7109 (Online), ISSN: 2230-9543 (Print).
[6] Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 815–823). Boston, MA, USA.
[7] Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014). DeepFace: Closing the gap to human-level performance in face verification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1701–1708). Columbus, OH, USA.
[8] Turk, M., & Pentland, A. (1991). Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1), 71–86.
[9] Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (Vol. 1, pp. I-511–I-518). Kauai, HI, USA.
How to cite this paper
@article{1719235,
author = {Dr. J. Narendra Babu, Aabid Ali, Akanksha M Shetty, Chaitra; Ajaya Suriya, Manoj K V ; Kalugotla Suresh Harshitha},
title = {IoT-Based Smart Attendance System Using Android Camera Streaming and Deep Learning Face Recognition},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {12},
pages = {2950-2957},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1719235.pdf},
abstract = {The growing demand for efficient, contactless, and automated attendance management in educational institutions has driven the development of intelligent systems that leverage Internet of Things (IoT) and artificial intelligence technologies. This paper presents the design and implementation of a Smart Attendance System that integrates an Android smart phone as a wireless IoT camera node, a Python-based deep learning service for real-time face recognition, and a full-stack web application for attendance management and analytics. The proposed system eliminates the limitations of traditional attendance methods such as manual roll calls, RFID cards, and fingerprint scanners by providing a completely contactless, hardware-minimal solution. The Android device streams live video over a local Wi-Fi network using the MJPEG protocol. A Python edge-computing service reads this stream using OpenCV, detects faces using Haar Cascade classifiers, and performs identity verification using the DeepFace library with the VGG-Face deep neural network model. Upon successful recognition, attendance records are automatically posted to a Node.js REST API and stored in a MongoDB database. The system features a React-based web dashboard for real-time monitoring, attendance logs, and R-powered statistical analytics including ARIMA-based forecasting and PDF report generation. Experimental results demonstrate that the system achieves reliable face recognition under standard indoor lighting conditions, marks attendance within seconds of recognition, and provides a scalable, cost-effective alternative to existing solutions. The system is built entirely on open-source technologies, requires no dedicated hardware beyond a standard Android smart phone and a laptop, and is deployable in any institution with a basic Wi-Fi infrastructure.},
keywords = {MPEG, ARIMA, WIFI, VGG Face},
month = {June},
doi = {https://doi.org/10.64388/IREV9I12-1719235}
}