Single Patch Based 3D High-Fidelity Mask Face Anti-Spoofing

Samuel Huang, Wen-Huang Cheng, Robert Cheng

ICCVW 2021 pp. 842-845

doi:10.1109/ICCVW54120.2021.00099 /iccvw/2021/huang2021iccvw-single/

Abstract

Face anti-spoofing is rapidly increasing in importance as facial recognition systems have become common in the financial and security fields. Among all kinds of attack, 3D high-fidelity masks are especially hard to defend. Recently, CASIA introduced a large scale dataset CASIA-SURF HiFiMask, which comprises of 54,600 videos recorded from 75 subjects with 225 high-fidelity masks. In this paper, we design a lightweight network with single patch input on the basis of CDCN++, and supervise it by focal loss. The proposed method achieves the Average Classification Error Rate (ACER) of 3.215 on the Protocol 3 of CASIASURF HiFiMask dataset and ranks the third best model in the Chalearn 3D High-Fidelity Mask Face Presentation Attack Detection Challenge at ICCV 2021.

ICCVW Semantic Scholar

Cite

Text

Huang et al. "Single Patch Based 3D High-Fidelity Mask Face Anti-Spoofing." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00099

Markdown

[Huang et al. "Single Patch Based 3D High-Fidelity Mask Face Anti-Spoofing." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/huang2021iccvw-single/) doi:10.1109/ICCVW54120.2021.00099

BibTeX

@inproceedings{huang2021iccvw-single,
  title     = {{Single Patch Based 3D High-Fidelity Mask Face Anti-Spoofing}},
  author    = {Huang, Samuel and Cheng, Wen-Huang and Cheng, Robert},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2021},
  pages     = {842-845},
  doi       = {10.1109/ICCVW54120.2021.00099},
  url       = {https://mlanthology.org/iccvw/2021/huang2021iccvw-single/}
}