Applied Research on Face Recognition Based on Transformer and Deep Reinforcement Learning

Shiyao Zhou

doi:10.54097/6zr2hg32

Authors

Shiyao Zhou

DOI:

https://doi.org/10.54097/6zr2hg32

Keywords:

Face Recognition, Transformer, Deep Reinforcement Learning, Deep Learning, Artificial Intelligence

Abstract

The progress of deep learning technology has greatly enhanced the performance of face recognition system, but there are also limitations such as low sample efficiency, unstable training, etc. Transformer is a revolutionary deep learning model architecture with the advantages of parallel computing and powerful long-range dependent modelling capability. This paper analyses the advantages and disadvantages of classical methods, deep reinforcement learning, Transformer and other methods applied in face recognition after reviewing many literatures, and concludes that the application of deep reinforcement learning combined with Transformer in face recognition is still in the early stage, but it has also achieved certain results, and it is a direction full of development potential in the field of artificial intelligence today.

Downloads

Download data is not yet available.

References

[1] Mazhar, M., Abid, M. H., Naveed, M., Siddiqui, M. F., & Kadri, B. (2024). Smart Automated Border Control System for Pakistan Airports Using ML-based Biometric Measures. Quaid-e-Awam University Research Journal of Engineering Science and Technology, 22(01), 1-18.

[2] Xue, S., Li, X., Du, Z., & Chen, D. (2024, October). Face generation combining text and sketch semantics. In Sixteenth International Conference on Digital Image Processing (ICDIP 2024) (Vol. 13274, pp. 704-711). SPIE.

[3] Belhumeur, P. N., Hespanha, J. P., & Kriegman, D. J. (1997). Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on pattern analysis and machine intelligence, 19(7), 711-720.

[4] Ojala, T., Pietikainen, M., & Maenpaa, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on pattern analysis and machine intelligence, 24(7), 971-987.

[5] Erwin, Azriansyah, M., Hartuti, N., Fachrurrozi, M., & Adhi Tama, B. (2019, March). A study about principle component analysis and eigenface for facial extraction. In Journal of Physics: Conference Series (Vol. 1196, No. 1, p. 012010). IOP Publishing.

[6] Putra, R. R. C., & Juniawan, F. P. (2017). Penerapan Algoritma Fisherfaces Untuk Pengenalan Wajah Pada Sistem Kehadiran Mahasiswa Berbasis Android. Telematika, 10(1), 132-146.

[7] Kumar, B. A., & Misra, N. K. (2025). A deep learning-based novel model for masked face recognition. Soft Computing, 1-22.

[8] Gaur, S., Pandey, M., & Himanshu. (2024). Realization of Facial Recognition Technology for Attendance Monitoring Through Biometric Modalities Employing MTCNN Integration. SN Computer Science, 5(7), 862.

[9] Zhong, Y., & Deng, W. (2021). Face transformer for recognition. arXiv preprint arXiv:2103.14803.

[10] He, L., He, L., & Peng, L. (2023). CFormerFaceNet: Efficient lightweight network merging a CNN and transformer for face recognition. Applied Sciences, 13(11), 6506.

[11] Cao, L., Yin, J., Guo, Y., Du, K., & Zhang, F. (2023). Sketch face recognition based on light semantic Transformer network. IET Computer Vision, 17(8), 962-976.

[12] Qin, L., Wang, M., Deng, C., Wang, K., Chen, X., Hu, J., & Deng, W. (2023). Swinface: a multi-task transformer for face recognition, expression recognition, age estimation and attribute estimation. IEEE Transactions on Circuits and Systems for Video Technology, 34(4), 2223-2234.