Authors :
Anurag Shandilya; Dr. Hare Ram Shah
Volume/Issue :
Volume 11 - 2026, Issue 6 - June
Google Scholar :
https://tinyurl.com/mvbdr243
Scribd :
https://tinyurl.com/r7ruxpc2
DOI :
https://doi.org/10.38124/ijisrt/26jun403
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Abstract :
Educational institutions continue to rely on manual attendance procedures that consume classroom time and
remain vulnerable to proxy attendance. Simultaneously, enforcing dress code policies and informing parents about
attendance irregularities often requires significant manual effort. This paper presents an integrated smart attendance
framework that combines face recognition, anti-spoofing liveness verification, automated dress code detection, and parental
notification within a single platform. The proposed system employs ArcFace-based facial recognition through the DeepFace
framework, Local Binary Pattern (LBP) texture analysis, Eye Aspect Ratio (EAR)-based blink detection, and HSV color
analysis with K-Means clustering for dress code verification. A FastAPI backend, Streamlit dashboard, and SQL-based
database support the complete workflow.
Keywords :
Smart Attendance System, Face Recognition, ArcFace, DeepFace, Liveness Detection, Dress Code Detection, Attendance Automation, Computer Vision, FastAPI, Streamlit.
References :
- J. Deng, J. Guo, N. Xue, and S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition,” Proc. IEEE/CVF CVPR, 2019.
- F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” Proc. IEEE/CVF CVPR, 2015.
- J. Maatta, A. Hadid, and M. Pietikainen, “Face Spoofing Detection from Single Images Using Micro-Texture Analysis,” Proc. IJCB, 2011.
- T. Soukupova and J. Cech, “Real-Time Eye Blink Detection Using Facial Landmarks,” CVWW, 2016.
- C. Lugaresi et al., “MediaPipe: A Framework for Perceiving and Processing Reality,” IEEE CVPR Workshop, 2019.
- Y. Zhang et al., “CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations,” ECCV, 2020.
- S. I. Serengil and A. Ozpinar, “LightFace: A Hybrid Deep Face Recognition Framework,” ASYU, 2020.
- K. Yamaguchi et al., “Parsing Clothes in Wildly Taken Photos,” IEEE/CVF CVPR, 2012.
- P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” IEEE CVPR, 2001.
- P. Raut et al., “IoT-Based Smart School Management System,” IJERT, 2018
Educational institutions continue to rely on manual attendance procedures that consume classroom time and
remain vulnerable to proxy attendance. Simultaneously, enforcing dress code policies and informing parents about
attendance irregularities often requires significant manual effort. This paper presents an integrated smart attendance
framework that combines face recognition, anti-spoofing liveness verification, automated dress code detection, and parental
notification within a single platform. The proposed system employs ArcFace-based facial recognition through the DeepFace
framework, Local Binary Pattern (LBP) texture analysis, Eye Aspect Ratio (EAR)-based blink detection, and HSV color
analysis with K-Means clustering for dress code verification. A FastAPI backend, Streamlit dashboard, and SQL-based
database support the complete workflow.
Keywords :
Smart Attendance System, Face Recognition, ArcFace, DeepFace, Liveness Detection, Dress Code Detection, Attendance Automation, Computer Vision, FastAPI, Streamlit.
