NextGen Attend: A Smart Attendance Management System

Author

Mr. B. Varun Kumar, Akalya M, Anusree K, Divya S


Abstract

 Attendance recording is a routine activity in educational institutions, yet manual roll calls and conventional attendance tools can consume classroom time and may be vulnerable to proxy attendance, recording mistakes, and fragmented record management. This paper presents NextGen Attend, a smart attendance management application designed to support classroom attendance through a webcam-based computer vision workflow. The system combines a React-based user interface, Python FastAPI backend services, MediaPipe-based face detection, and MySQL data management. Its workflow includes student registration, live face detection, recognition against registered student information, a head-movement-based liveness check, automatic attendance marking, unknown-face handling, and spoken confirmation through the Web Speech API. A bulk-registration module supports importing student details and photographs from a prepared PDF, alongside separate upload options. Faculty and student interfaces provide role-oriented access to attendance operations and records. The paper describes the architecture, processing workflow, implementation components, and development observations of the prototype. Since controlled evaluation metrics have not been supplied, the manuscript does not claim measured recognition accuracy, spoof-resistance rates, or time savings. These outcomes require systematic testing under varied classroom conditions. The work demonstrates a practical integration of browser-based interaction, backend services, face-processing components, and database persistence for a college attendance workflow.



Keywords

Smart Attendance, Face Detection, Face Recognition, Liveness Detection, Computer Vision, FastAPI, MediaPipe, MySQL, Web Speech API



Full Text:

Download Paper PDF


References


  • Viola and M. J. Jones, “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), 2001, vol. 1, pp. I-511–I-518. doi: 10.1109/CVPR.2001.990517.\
  • Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 815–823. doi: 10.1109/CVPR.2015.7298682.
  • Ramachandra and C. Busch, “Presentation Attack Detection Methods for Face Recognition Systems: A Comprehensive Survey,” ACM Computing Surveys, vol. 50, no. 1, Article 8, pp. 1–37, 2017. doi: 10.1145/3038924.
  • Google AI for Developers, “MediaPipe Face Detector,” MediaPipe documentation. Available: https://ai.google.dev/edge/mediapipe/solutions/vision/face_detector. Accessed: 3 Nov. 2026.
  • FastAPI, “FastAPI Documentation.” Available: https://fastapi.tiangolo.com/. Accessed: 3 Nov. 2026.
  • React, “React Documentation.” Available: https://react.dev/. Accessed: 3 Nov. 2026.
  • Oracle, “MySQL 8.4 Reference Manual.” Available: https://dev.mysql.com/doc/. Accessed: 3 Nov. 2026.
  • MDN Web Docs, “Web Speech API.” Available: https://developer.mozilla.org/en-US/docs/Web/API/Web_Speech_API. Accessed: 3 Nov. 2026.
  • Agustiyar, A., Isnanto, R. R., Widodo, C. E., and Zaini, N. A. B. (2025). “A Systematic Literature Review of Face Recognition Based Attendance System: Methods, Trends, and Research Gaps.” This study reviews face recognition methods, feature extraction techniques, and research challenges in automated attendance systems. ResearchGate
  • Google AI Edge (2025). “MediaPipe Face Detector Documentation.” This documentation explains the use of face detection models to locate faces in images and video streams, supporting the webcam-based face detection component of NextGen Attend.CCN+1

Share your valuable work from Social Media Buttons