Edge-based Face Recognition Pipeline Optimization for Class Attendance System

Mutia Fadhilla, Rizky Wandri, Des Suryani, Yudhi Arta

Abstract


Manual attendance recording remains inefficient and may enable proxy attendance, while cloud-based facial recognition introduces network dependency, latency, and biometric-data privacy concerns. Edge processing offers a local alternative, but limited computing resources require pipeline optimization. This study conducted a descriptive single-run evaluation of five optimization strategies on a Raspberry Pi 5: frame downscaling, static region of interest (ROI), prototype caching, sample interval tuning, and face detector comparison. The pipeline used FaceNet embeddings, cosine-similarity-based open-set recognition, and track-based temporal confirmation. Evaluation involved three prerecorded 1920 × 1080 classroom videos totaling 16 min 23 s, an enrollment database of 18 students, and 53 student-video attendance instances. Frame downscaling at 0.75 reduced runtime from 1,274.83 s to 947.72 s, equivalent to 25.66%, while confirmed attendance instances decreased slightly from 47 to 46. Effective sampled-frame throughput increased by 34.62%, and average RAM usage decreased by 6.86%, although CPU utilization and peak temperature increased. Prototype caching reduced preparation time but had limited effect on end-to-end runtime, whereas static ROI, sampling intervals above 5 s, and YuNet did not improve overall pipeline performance. Frame downscaling was therefore the most promising strategy in the evaluated setup. However, repeated trials and independent classroom-video testing are required before generalizing the results or considering the pipeline deployment-ready.

Keywords


attendance system; edge computing; face recognition; pipeline optimization; raspberry pi

Full Text:

PDF

References


R. Wandri, M. Fadhilla, D. F. Qurniawan, and E. D. Saputra, “Implementation of a Face Recognition API for an Automated Web-based Attendance System using Extreme Programming,” Sistemasi: Jurnal Sistem Informasi, Vol. 15, No. 6, Jun. 2026, [Online]. Available: http://sistemasi.ftik.unisi.ac.id

R. Rahmayani, S. Saniman, and T. Tugiono, “Perancangan Sistem Sidik Jari Absensi Siswa SMP dengan menggunakan Node MCU yang Terhubung dengan Telegram,” Jurnal Sistem Komputer Triguna Dharma (JURSIK TGD), Vol. 2, No. 2, pp. 132–138, Mar. 2023, DOI: 10.53513/jursik.v2i2.7193.

Asep Mahpudin and Agam Hamdani, “Perancangan Sistem Informasi Absensi Sekolah berbasis Web,” ICT Learning, Vol. 6, No. 2, Dec. 2022, DOI: 10.33222/ictlearning.v6i2.2766.

H. Harizahayu, F. Friendly, R. W. Sembiring, and P. H. Putra, “Perancangan dan Penerapan Sistem Pencatatan Kehadiran Siswa pada SMK Yayasan Pendidikan Mulia Kecamatan Medan Selayang Sumatera Utara,” SWARNA: Jurnal Pengabdian Kepada Masyarakat, Vol. 3, No. 2, pp. 134–140, Feb. 2024, DOI: 10.55681/swarna.v3i2.997.

J. Budiasto, H. Jayawardana, and F. A. K. Dewi, “Sistem Informasi Pencatatan Absensi Siswa berbasis Website pada SMA Negeri 1 Kurik,” Musamus Journal of Technology & Information, Vol. 5, No. 02, pp. 066–071, Apr. 2023, DOI: 10.35724/mjti.v5i02.5384.

M. Fadhilla, R. Wandri, A. Hanafiah, P. R. Setiawan, Y. Arta, and S. Daulay, “Analisis Performa Algoritma Machine Learning untuk Identifikasi Depresi pada Mahasiswa,” Journal of Informatics Management and Information Technology, Vol. 5, No. 1, 2025.

X. Li, S. Lai, and X. Qian, “DBCFace: Towards Pure Convolutional Neural Network Face Detection,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 32, No. 4, pp. 1792–1804, Apr. 2022, DOI: 10.1109/TCSVT.2021.3082635.

C. Oinar, B. M. Le, and S. S. Woo, “KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition,” IEEE Access, Vol. 11, pp. 137138–137150, 2023, DOI: 10.1109/ACCESS.2023.3338648.

G. Vardakis, G. Tsamis, E. Koutsaki, K. Haridimos, and N. Papadakis, “Smart Home: Deep Learning as a Method for Machine Learning in Recognition of Face, Silhouette and Human Activity in the Service of a Safe Home,” Electronics (Switzerland), Vol. 11, No. 10, May 2022, DOI: 10.3390/electronics11101622.

G. Rajeshkumar et al., “Smart Office Automation via Faster R-CNN based Face Recognition and Internet of Things,” Measurement: Sensors, Vol. 27, Jun. 2023, DOI: 10.1016/j.measen.2023.100719.

P. P. Oroceo, J. I. Kim, E. M. F. Caliwag, S. H. Kim, and W. Lim, “Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network,” Sensors, Vol. 22, No. 21, Nov. 2022, DOI: 10.3390/s22218371.

H. Hua, Y. Li, T. Wang, N. Dong, W. Li, and J. Cao, “Edge Computing with Artificial Intelligence: A Machine Learning Perspective,” ACM Comput. Surv., Vol. 55, No. 9, Sep. 2023, DOI: 10.1145/3555802.

A. Koubaa, A. Ammar, A. Kanhouch, and Y. Alhabashi, “Cloud Versus Edge Deployment Strategies of Real-Time Face Recognition Inference,” IEEE Trans. Netw. SCI. Eng., Vol. 9, No. 1, pp. 143–160, 2022, DOI: 10.1109/TNSE.2021.3055835.

S. S. Khan, D. Sengupta, A. Ghosh, and A. Chaudhuri, “MTCNN++: A CNN-based Face Detection Algorithm Inspired by MTCNN,” Visual Computer, Vol. 40, No. 2, pp. 899–917, Feb. 2024, DOI: 10.1007/s00371-023-02822-0.

S. Sony Priya and R. I. Minu, “Augmenting Face Detection in Extremely Low-Light CCTV Footage using the EDCE Enhancement Model,” Traitement du Signal, Vol. 40, No. 6, pp. 2741–2750, Dec. 2023, DOI: 10.18280/ts.400634.

M. A. Hasan, “Facial Human Emotion Recognition by using YOLO Faces Detection Algorithm,” JOINCS (Journal of Informatics, Network, and Computer Science), Vol. 6, No. 2, pp. 32–38, Nov. 2023, DOI: 10.21070/joincs.v6i2.1629.

A. George, C. Ecabert, H. O. Shahreza, K. Kotwal, and S. Marcel, “EdgeFace: Efficient Face Recognition Model for Edge Devices,” IEEE Trans. Biom. Behav. Identity SCI., Vol. 6, No. 2, 2024, DOI: 10.1109/TBIOM.2024.3352164.

W. Wu, H. Peng, and S. Yu, “YuNet: A Tiny Millisecond-Level Face Detector,” Machine Intelligence Research, Vol. 20, No. 5, 2023, DOI: 10.1007/s11633-023-1423-y.

S. Minakova and T. Stefanov, “Memory-Throughput Trade-off for CNN-based Applications at the Edge,” ACM Transact. Des. Autom. Electron. Syst., Vol. 28, No. 1, Dec. 2022, DOI: 10.1145/3527457.

Q. Qi, Y. Lu, J. Li, J. Wang, H. Sun, and J. Liao, “Learning Low Resource Consumption CNN through Pruning and Quantization,” IEEE Trans. Emerg. Top. Comput., Vol. 10, No. 2, pp. 886–903, 2022, DOI: 10.1109/TETC.2021.3050770.

S. L. Chu, C. F. Chen, and Y. C. Zheng, “CFSM: A Novel Frame Analyzing Mechanism for Real-Time Face Recognition System on the Embedded System,” Multimed. Tools Appl., Vol. 81, No. 2, 2022, DOI: 10.1007/s11042-021-11599-0.

M. Parhi, A. Roul, B. Ghosh, and A. Pati, “IOATS: An Intelligent Online Attendance Tracking System based on Facial Recognition and Edge Computing,” Original Research Paper International Journal of Intelligent Systems and Applications in Engineering IJISAE, Vol. 2022, No. 2, pp. 252–259, 2022, DOI: 10.1039/b000000x.

A. Agus Kurniasari, I. G. Wiryawan, T. Rizaldi, P. S. D. Puspitasari, D. M. P. Ernanta, and S. P. Sari, “Intelligence Attendance Monitoring System using Real-Time Face Recognition and Raspberry Pi ‘Intelligence Attendance Monitoring System using Real-Time Face Recognition and Raspberry Pi,’” Matrix: Jurnal Manajemen Teknologi dan Informatika, Vol. 15, No. 2, pp. 102–113, 2025, DOI: 10.31940/matrix.v15i2.102-113.

J. Jeong, B. Kim, J. Yu, and Y. Yoo, “EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection,” in Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024, 2024. DOI: 10.1109/WACV57701.2024.00103.

K. Gkrispanis, N. Gkalelis, and V. Mezaris, “Filter-Pruning of Lightweight Face Detectors using a Geometric Median Criterion,” in Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2024, 2024. DOI: 10.1109/WACVW60836.2024.00037.

A. Baobaid and M. Meribout, “Edge-GPU based Face Tracking for Face Detection and Recognition Acceleration,” IEEE Internet Things J., 2026, DOI: 10.1109/JIOT.2026.3701825.

O. A. Naser, S. Mumtazah, K. Samsudin, M. Hanafi, S. M. B. Shafie, and N. Z. Zamri, “Comparative Analysis of MTCNN and Haar Cascades for Face Detection in Images with Variation in Yaw Poses and Facial Occlusions,” Journal of Communications Software and Systems, Vol. 21, No. 1, 2025, DOI: 10.24138/jcomss-2024-0084.




DOI: https://doi.org/10.32520/stmsi.v15i9.6918

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.