One-Class Learning Method Based on Live Correlation Loss for Face Anti-Spoofing

被引:6
作者
Lim, Seokjae [1 ]
Gwak, Yongjae [1 ]
Kim, Wonjun [1 ]
Roh, Jong-Hyuk [2 ]
Cho, Sangrae [2 ]
机构
[1] Konkuk Univ, Dept Elect & Elect Engn, Seoul 05029, South Korea
[2] Elect & Telecommun Res Inst, Daejeon 34129, South Korea
关键词
Biometric authentication systems; face anti-spoofing; one-class learning; live correlation loss; feature correlation network; DOMAIN ADAPTATION; IMAGE;
D O I
10.1109/ACCESS.2020.3035747
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
As biometric authentication systems are popularly used in various mobile devices, e.g., smart-phones and tablets, face anti-spoofing methods have been actively developed for the high-level security. However, most previous approaches still suffer from diverse types of spoofing attacks, which are hardly covered by the limited number of training datasets, and thus they often show the poor accuracy when unseen samples are given for the test. To address this problem, a novel method for face anti-spoofing is proposed based on one-class (i.e., live face only) learning with the live correlation loss. Specifically, encoder-decoder networks are firstly trained with only live faces to extract latent features, which have an ability to compactly represent various live facial properties in the embedding space and produce the spoofing cues, which are simply obtained by subtracting the original RGB image and the generated one. After that, such features are fed into the proposed feature correlation network (FCN) so that weights of FCN learn to compute "liveness" of given features under the guidance of the live correlation loss. It is noteworthy that the proposed method only requires live facial images for training the model, which are easier to obtain than fake ones, and thus the generality power for resolving the problem of face anti-spoofing can be expected to be improved. Experimental results on various benchmark datasets demonstrate the efficiency and robustness of the proposed method.
引用
收藏
页码:201635 / 201648
页数:14
相关论文
共 36 条
  • [21] Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
    Liu, Yaojie
    Jourabloo, Amin
    Liu, Xiaoming
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 389 - 398
  • [22] Maatta Jukka, 2011, P 2011 INT JOINT C B, P1, DOI [DOI 10.1109/IJCB.2011.6117510, 10.1109/IJCB.2011.6117510]
  • [23] Parkhi Omkar M, 2015, BMVC
  • [24] Paszke Adam, 2017, ADV NEUR INF PROC SY
  • [25] Secure Face Unlock: Spoof Detection on Smartphones
    Patel, Keyurkumar
    Han, Hu
    Jain, Anil K.
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2016, 11 (10) : 2268 - 2283
  • [26] Peixoto Bruno, 2011, 2011 18th IEEE International Conference on Image Processing (ICIP 2011), P3557, DOI 10.1109/ICIP.2011.6116484
  • [27] Multi-adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
    Shao, Rui
    Lan, Xiangyuan
    Li, Jiawei
    Yuen, Pong C.
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 10015 - 10023
  • [28] Face Spoofing Detection Based on Local Ternary Label Supervision in Fully Convolutional Networks
    Sun, Wenyun
    Song, Yu
    Chen, Changsheng
    Huang, Jiwu
    Kot, Alex C.
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 : 3181 - 3196
  • [29] A Face Spoofing Detection Method Based on Domain Adaptation and Lossless Size Adaptation
    Sun, Wenyun
    Song, Yu
    Zhao, Haitao
    Jin, Zhong
    [J]. IEEE ACCESS, 2020, 8 : 66553 - 66563
  • [30] Face Liveness Detection from a Single Image with Sparse Low Rank Bilinear Discriminative Model
    Tan, Xiaoyang
    Li, Yi
    Liu, Jun
    Jiang, Lin
    [J]. COMPUTER VISION - ECCV 2010, PT VI, 2010, 6316 : 504 - 517