A Review of Face Recognition Technology: From Algorithms to Real-Time Systems with InsightFace

Jiakun Chen

doi:10.54691/a68wvc11

Authors

Jiakun Chen

DOI:

https://doi.org/10.54691/a68wvc11

Keywords:

Face recognition, ArcFace, deep learning, feature extraction, real-time application.

Abstract

Facial recognition, a key biometric technology, is widely used in fields such as security monitoring, identity verification, and mobile devices due to its convenience, non-intrusiveness, and intuitive nature. However, challenges still exist in complex scenarios involving variations in lighting, angle, occlusion, and multi-object detection. This study evaluates the performance and limitations of current facial recognition technologies, proposing a prototype real-time system developed using the open-source InsightFace framework. The research employs a combination of literature review and empirical testing, where recent advancements in algorithm selection, model optimization, and system integration are summarized. Next, a prototype system based on InsightFace is constructed and tested using both self-collected and publicly available datasets, including LFW and AgeDB. The results demonstrate that under optimal conditions (good lighting and frontal faces), the system achieves recognition accuracy above 90%, with a response time of under 200 milliseconds. However, performance declines under occlusion or significant changes in posture. This study highlights how combining high-performance open-source models with effective feature matching strategies can meet real-time operational requirements while maintaining recognition accuracy. The findings offer a cost-effective solution for developers with limited resources, such as student teams and small businesses, and provide a foundation for future applications in mobile and multi-scenario environments.

Downloads

Download data is not yet available.

References

[1] Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014). DeepFace: Closing the gap to human-level performance in face verification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1701–1708. https://doi.org/10.1109/CVPR.2014.220

[2] Sun, Y., Wang, X., & Tang, X. (2014). DeepID: Face verification with deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1701–1708. https://doi.org/10.1109/CVPR.2014.220

[3] Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 815–823. https://doi.org/10.1109/CVPR.2015.7298682

[4] Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019). ArcFace: Additive angular margin loss for deep face recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4690–4699. https://doi.org/10.1109/CVPR.2019.00482

[5] DeepInsight. (2025, August 29). InsightFace. GitHub. https://github.com/deepinsight/insightface

[6] Chen, S., Chen, C., Zhang, X., & Huang, K. (2018). MobileFaceNets: Efficient CNNs for accurate real-time face verification on mobile devices. In Z. Sun & C. Shan (Eds.), Biometric Recognition (CCBR 2018). Lecture Notes in Computer Science (Vol. 10996, pp. 428–438). Springer. https://doi.org/10.1007/978-3-030-02257-3_46

[7] Zhang, Q., Zhang, X., & Wang, Y. (2020). ShuffleFaceNet: A lightweight face recognition network for mobile devices. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 1–12. https://doi.org/10.1007/978-3-030-58536-5_29

[8] Huang, T., Li, X., & Zhang, Y. (2021). Differential privacy in face recognition: A survey. arXiv. https://arxiv.org/abs/2105.12182

[9] Peng, X., Li, Y., & Zhao, Z. (2022). Unsupervised domain adaptation for face recognition: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12), 9649–9667. https://doi.org/10.1109/TPAMI.2021.3054824

[10] Buolamwini, J., & Gebru, T. (2018). Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency (FAT) (pp. 77–91). ACM. https://doi.org/10.1145/3287560.3287572