Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario

Face anti-spoofing is the key to preventing security breaches in biometric recognition applications. Existing software-based and hardware-based face liveness detection methods are effective in constrained environments or designated datasets only. Deep learning method using RGB and infrared images demands a large amount of training data for new attacks. In this paper, we present a face anti-spoofing method in a real-world scenario by automatic learning the physical characteristics in polarization images of a real face compared to a deceptive attack. A computational framework is developed to extract and classify the unique face features using convolutional neural networks and SVM together. Our real-time polarized face anti-spoofing (PAAS) detection method uses a on-chip integrated polarization imaging sensor with optimized processing algorithms. Extensive experiments demonstrate the advantages of the PAAS technique to counter diverse face spoofing attacks (print, replay, mask) in uncontrolled indoor and outdoor conditions by learning polarized face images of 33 people. A four-directional polarized face image dataset is released to inspire future applications within biometric anti-spoofing field.

[1]  Nalini K. Ratha,et al.  Fake iris detection using structured light , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Xiaoming Liu,et al.  Face De-Spoofing: Anti-Spoofing via Noise Modeling , 2018, ECCV.

[5]  M. Hubert,et al.  Multivariate Functional Halfspace Depth , 2012 .

[6]  Michael Wagner,et al.  Liveness Verification in Audio-Video Speaker Authentication , 2004 .

[7]  Jukka Komulainen,et al.  Face Spoofing Detection Using Colour Texture Analysis , 2016, IEEE Transactions on Information Forensics and Security.

[8]  Lin Sun,et al.  Eyeblink-based Anti-Spoofing in Face Recognition from a Generic Webcamera , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[9]  Gang Li,et al.  Recent Progress on Distributed Structural Health Monitoring Research at NUAA , 2008 .

[10]  Stan Z. Li,et al.  Face liveness detection by learning multispectral reflectance distributions , 2011, Face and Gesture 2011.

[11]  Guoying Zhao,et al.  3D Mask Face Anti-spoofing with Remote Photoplethysmography , 2016, ECCV.

[12]  Hong Wei,et al.  Face anti-spoofing countermeasure: Efficient 2D materials classification using polarization imaging , 2017, 2017 5th International Workshop on Biometrics and Forensics (IWBF).

[13]  Terrance E. Boult,et al.  PARAPH: Presentation Attack Rejection by Analyzing Polarization Hypotheses , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Abdenour Hadid,et al.  Face Biometrics Under Spoofing Attacks: Vulnerabilities, Countermeasures, Open Issues, and Research Directions , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[15]  Lei Huang,et al.  Context based face spoofing detection using active near-infrared images , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[16]  Fei Liu,et al.  A novel IR polarization imaging system designed by a four-camera array , 2014, Sensing Technologies + Applications.

[17]  Samarth Bharadwaj,et al.  Face anti-spoofing via motion magnification and multifeature videolet aggregation , 2014 .

[18]  Olegs Nikisins,et al.  Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network , 2019, IEEE Transactions on Information Forensics and Security.

[19]  Josef Bigün,et al.  Evaluating liveness by face images and the structure tensor , 2005, Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05).

[20]  Javier Hernandez-Ortega,et al.  Time Analysis of Pulse-Based Face Anti-Spoofing in Visible and NIR , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[21]  Shifeng Zhang,et al.  A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Matti Pietikäinen,et al.  Face spoofing detection from single images using micro-texture analysis , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[23]  Sangyoun Lee,et al.  Face Liveness Detection Using a Light Field Camera , 2014, Sensors.

[24]  Meng Pan,et al.  A Review of Face Anti-spoofing and Its Applications in China , 2019 .

[25]  Paulo Lobato Correia,et al.  Face spoofing detection using a light field imaging framework , 2018, IET Biom..

[26]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Kiran B. Raja,et al.  Face Presentation Attack Detection by Exploring Spectral Signatures , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[28]  M. Vedel,et al.  Full Stokes polarization imaging camera , 2011, Optical Engineering + Applications.