Biometrics utilize physiological, such as fingerprint, face, and iris, or behavioral characteristics, such as typing rhythm and gait, to uniquely identify or authenticate an individual. As biometric systems are widely used in real-world applications including mobile phone authentication and access control, biometric spoof, or Presentation Attack (PA) are becoming a larger threat, where a spoofed biometric sample is presented to the biometric system and attempted to be authenticated. Since face is the most accessible biometric modality, there have been many different types of PAs for faces including print attack, replay attack, 3D masks, etc. As a result, conventional face recognition systems can be very vulnerable to such PAs. We proposes a novel two-stream CNN-based face antispoofing method, for print and replay attacks. The proposed method extracts the local features and holistic depth maps from face images.

Overview Face Recon

Figure 1: Architecture of the proposed face anti-spoofing approach.

PC Demo

Mobile Demo

Publications

  • Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
    Yaojie Liu*, Amin Jourabloo*, Xiaoming Liu
    In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, Jun. 2018
    Bibtex | PDF | arXiv
  • @inproceedings{ learning-deep-models-for-face-anti-spoofing-binary-or-auxiliary-supervision,
      author = { Yaojie Liu* and Amin Jourabloo* and Xiaoming Liu },
      title = { Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision },
      booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
      address = { Salt Lake City, UT },
      month = { June },
      year = { 2018 },
    }
  • Face Anti-Spoofing Using Patch and Depth-based CNNs
    Yousef Atoum, Yaojie Liu, Amin Jourabloo, Xiaoming Liu
    In Proceeding of International Joint Conference on Biometrics (IJCB 2017), Denver, CO, Oct. 2017
    Bibtex | PDF
  • @inproceedings{ face-anti-spoofing-using-patch-and-depth-based-cnns,
      author = { Yousef Atoum and Yaojie Liu and Amin Jourabloo and Xiaoming Liu },
      title = { Face Anti-Spoofing Using Patch and Depth-based CNNs },
      booktitle = { In Proceeding of International Joint Conference on Biometrics },
      address = { Denver, CO },
      month = { October },
      year = { 2017 },
    }