TY - GEN
T1 - Deep convolutional dynamic texture learning with adaptive channel-discriminability for 3D mask face anti-spoofing
AU - Shao, Rui
AU - Lan, Xiangyuan
AU - Yuen, Pong C.
N1 - Funding Information:
This project is partially supported by Hong Kong RGC General Research Fund HKBU 12201215.
PY - 2017/7/1
Y1 - 2017/7/1
N2 - 3D mask spoofing attack has been one of the main challenges in face recognition. A real face displays a different motion behaviour compared to a 3D mask spoof attempt, which is reflected by different facial dynamic textures. However, the different dynamic information usually exists in the subtle texture level, which cannot be fully differentiated by traditional hand-crafted texture-based methods. In this paper, we propose a novel method for 3D mask face anti-spoofing, namely deep convolutional dynamic texture learning, which learns robust dynamic texture information from fine-grained deep convolutional features. Moreover, channel-discriminability constraint is adaptively incorporated to weight the discriminability of feature channels in the learning process. Experiments on both public datasets validate that the proposed method achieves promising results under intra and cross dataset scenario.
AB - 3D mask spoofing attack has been one of the main challenges in face recognition. A real face displays a different motion behaviour compared to a 3D mask spoof attempt, which is reflected by different facial dynamic textures. However, the different dynamic information usually exists in the subtle texture level, which cannot be fully differentiated by traditional hand-crafted texture-based methods. In this paper, we propose a novel method for 3D mask face anti-spoofing, namely deep convolutional dynamic texture learning, which learns robust dynamic texture information from fine-grained deep convolutional features. Moreover, channel-discriminability constraint is adaptively incorporated to weight the discriminability of feature channels in the learning process. Experiments on both public datasets validate that the proposed method achieves promising results under intra and cross dataset scenario.
UR - http://www.scopus.com/inward/record.url?scp=85046265476&partnerID=8YFLogxK
U2 - 10.1109/BTAS.2017.8272765
DO - 10.1109/BTAS.2017.8272765
M3 - Conference proceeding
AN - SCOPUS:85046265476
T3 - IEEE International Joint Conference on Biometrics, IJCB 2017
SP - 748
EP - 755
BT - IEEE International Joint Conference on Biometrics, IJCB 2017
PB - IEEE
T2 - 2017 IEEE International Joint Conference on Biometrics, IJCB 2017
Y2 - 1 October 2017 through 4 October 2017
ER -