TY - GEN
T1 - Single Patch Based 3D High-Fidelity Mask Face Anti-Spoofing
AU - Huang, Samuel
AU - Cheng, Wen-Huang
AU - Cheng, Robert
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85121760665&partnerID=8YFLogxK
U2 - 10.1109/ICCVW54120.2021.00099
DO - 10.1109/ICCVW54120.2021.00099
M3 - Conference contribution
AN - SCOPUS:85121760665
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 842
EP - 845
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Y2 - 11 October 2021 through 17 October 2021
ER -