Face anti-spoofing with joint spoofing medium detection and eye blinking analysis

Nikitin M.Yu.1,2, Konushin V.S.2, Konushin A.S.1,3

1 M.V. Lomonosov Moscow State University, Moscow, Russia,

2 Video Analysis Techonologies LLC, Moscow, Russia,

3 National Research University Higher School of Economics, Moscow, Russia

Аннотация:
Modern biometric systems based on face recognition demonstrate high recognition quality, but they are vulnerable to face presentation attacks, such as photo or replay attack. Existing face anti-spoofing methods are mostly based on texture analysis and due to lack of training data either use hand-crafted features or fine-tuned pretrained deep models. In this paper we present a novel CNN-based approach for face anti-spoofing, based on joint analysis of the presence of a spoofing medium and eye blinking. For training our classifiers we propose the procedure of synthetic data generation which allows us to train powerful deep models from scratch. Experimental analysis on the challenging datasets (CASIA-FASD, NUUA Imposter) shows that our method can obtain state-of-the-art results.

Ключевые слова:
face anti-spoofing, synthetic data, video analysis, neural networks, deep learning

Цитирование:
Nikitin MYu, Konushin VS, Konushin AS. Face anti-spoofing with joint spoofing medium detection and eye blinking analysis. Computer Optics 2019; 43(4): 618-626. DOI: 10.18287/2412-6179-2019-43-4-618-626.

Литература:

  1. Zhang, Z. A face antispoofing database with diverse attacks / J. Yan, S. Liu, Z. Lei, D. Yi, S.Z. Li // 5th IEEE International Conference on Biometrics (ICB). – 2012. – P. 26-31.
  2. Tan, X. Face liveness detection from a single image with sparse low rank bilinear discriminative model / X. Tan, Y. Li, J. Liu, L. Jiang // European Conference on Computer Vision (ECCV). – 2010. – P. 504-517.
  3. Komulainen, J. Context based face anti-spoofing / J. Komulainen, A. Hadid, M. Pietikainen // 6th IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS). – 2013. – P. 1-8.
  4. Yang, J. Face liveness detection with component dependent descriptor / J. Yang, Z. Lei, S. Liao, S.Z. Li // 6th IEEE International Conference on Biometrics (ICB). – 2013. – P. 1-6.
  5. De Freitas Pereira, T. Face liveness detection using dynamic texture / T. De Freitas Pereira, J. Komulainen, A. Anjos, J.M. De Martino, A. Hadid, M. Pietikinen, S. Marcel // EURASIP Journal on Image and Video Processing. – 2014. – 2.
  6. Peixoto, B. Face liveness detection under bad illumination conditions / B. Peixoto, C. Michelassi, A. Rocha // 18th IEEE International Conference on Image Processing (ICIP). – 2011. – P. 3557-3560.
  7. Patel, K. Secure face unlock: Spoof detection on smartphones / K. Patel, H. Han, A. Jain // IEEE transactions on information forensics and security. – 2016. – Vol. 11, Is-sue 10. – P. 2268-2283.
  8. Komulainen, J. Face spoofing detection using dynamic texture / J. Komulainen, A. Hadid, M. Pietikinen // Asian Conference on Computer Vision (ACCV). – 2012. – P. 146-157.
  9. Boulkenafet, Z. Face anti-spoofing based on color texture analysis / Z. Boulkenafet, J. Komulainen, A. Hadid // 22nd IEEE International Conference on Image Processing (ICIP). – 2015. – P. 2636-2640.
  10. De Freitas Pereira, T. LBP-TOP based countermeasure against face spoofing attacks / T. De Freitas Pereira, A. Anjos, J.M. De Martino, S. Marcel // Asian Conference on Computer Vision (ACCV). – 2012. – P. 121-132.
  11. De Freitas Pereira, T. Can face anti-spoofing countermeasures work in a real world scenario? / T. De Freitas Pereira, A. Anjos, J.M. De Martino, S. Marcel // 6th IEEE International Conference on Biometrics (ICB). – 2013. – P. 1-8.
  12. Boulkenafet, Z. Face anti-spoofing using speeded-up robust features and fisher vector encoding / Z. Boulkenafet, J. Komulainen, A. Hadid // IEEE Signal Processing Letters. – 2017. – Vol. 24, Issue 2. – P. 141-145.
  13. Atoum, Y. Face anti-spoofing using patch and depth-based CNNs / Y. Atoum, Y. Liu, A. Jourabloo, X. Liu // IEEE International Joint Conference on Biometrics (IJCB). – 2017. – P. 319-328.
  14. Pan, G. Eyeblink-based anti-spoofing in face recognition from a generic webcamera / G. Pan, L. Sun, Z. Wu, S. Lao // 11th IEEE International Conference on Computer Vision (ICCV). – 2007. – P. 1-8.
  15. Sun, L. Blinking-based live face detection using conditional random fields / L. Sun, G. Pan, Z. Wu, S. Lao // International Conference on Biometrics (ICB). – 2007. – P. 252-260.
  16. Patel, K. Cross-database face anti-spoofing with robust feature representation / K. Patel, H. Han, A.K. Jain // Chinese Conference on Biometric Recognition. – 2016. – P. 611-619.
  17. Kollreider, K. Real-time face detection and motion analysis with application in liveness assessment / K. Kollreider, H. Fronthaler, M.I. Faraj, J. Bigun // IEEE Transactions on Information Forensics and Security. – 2007. – Vol. 2, Issue 3. – P. 548-558.
  18. Shao, R. Deep convolutional dynamic texture learning with adaptive channel-discriminability for 3D mask face anti-spoofing / R. Shao, X. Lan, P.C. Yuen // IEEE International Joint Conference on Biometrics (IJCB). – 2017. – P. 748-755.
  19. Kollreider, K. Non-intrusive liveness detection by face images / K. Kollreider, H. Fronthaler, J. Bigun // Image and Vision Computing. – 2009. – Vol. 27, Issue 3. – P. 233-244.
  20. Bao, W. A liveness detection method for face recognition based on optical flow field / W. Bao, H. Li, N. Li, W. Jiang // IEEE Image Analysis and Signal Processing (IASP). – 2009. – P. 233-236.
  21. Bharadwaj, S. Face antispoofing via motion magnification and multifeature videolet aggregation / S. Bharadwaj, T.I. Dhamecha, M. Vatsa, R. Singh. – 2014. – URL: https://repository.iiitd.edu.in/jspui/handle/123456789/138 (request date 04.06.2019).
  22. Feng, L. Integration of image quality and motion cues for face anti-spoofing: A neural network approach / L. Feng, L.M. Po, Y. Li, X. Xu, F.Yuan, T.C.H. Cheung, K.W. Cheung // Journal of Visual Communication and Image Representation. – 2016. – Vol. 38. – P. 451-460.
  23. Xu, Z. Learning temporal features using LSTM-CNN architecture for face anti-spoofing / Z. Xu, S. Li, W. Deng // 3rd IEEE Asian Conference on Pattern Recognition (ACPR). – 2015. – P. 141-145.
  24. Tronci, R. Fusion of multiple clues for photo-attack detection in face recognition systems / R. Tronci, D. Mutoni, G. Fadda, M. Pili, N. Sirena, G. Murgia, M. Ristori, S. Recerche, F. Roli // IEEE International Joint Conference on Biometrics (IJCB). – 2011. – P. 1-6.
  25. Yang, J. Learn convolutional neural network for face anti-spoofing / J. Yang, Z. Lei, S.Z. Li. – 2014. – URL: https://arxiv.org/abs/1408.5601 (request date 04.06.2019).
  26. Li, L. An original face anti-spoofing approach using partial convolutional neural network / L. Li, X. Feng, Z. Boulkenafet, Z. Xia, M. Li, A. Hadid // IEEE Image processing theory tools and applications (IPTA). – 2016. – P. 1-6.
  27. Video Analysis Technologies. FaceSDK, facial analysis library. – URL: https://tevian.ru/product/facesdk/ (request date 04.06.2019).
  28. He, K. Deep residual learning for image recognition / K. He, X. Zhang, S. Ren, J. Sun // IEEE Conference on Computer Vision and Pattern Recognition (CVPR). – 2016. – P. 770-778.
  29. Song, F. Eyes closeness detection from still images with multi-scale histograms of principal oriented gradients / F. Song, X. Tan, X. Liu, S. Chen // Pattern Recognition. – 2014. – Vol. 47, Issue 9. – P. 2825-2838.
  30. Chen, T. MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems / T. Chen, M. Li, Y. Li, M. Lin, N. Wang, M. Wang, T. Xiao, B. Xu, C. Zhang, Z. Zhang. – 2015. – URL: https://arxiv.org/abs/1512.01274 (request date 04.06.2019).
  31. Song, X. Face spoofing detection by fusing binocular depth and spatial pyramid coding micro-texture features / X. Song, X. Zhao, T. Lin // IEEE International Conference on Image Processing (ICIP). – 2017. – P. 96-100.
  32. Yu, C. Anisotropic diffusion-based kernel matrix model for face liveness detection / C. Yu, Y. Jia. – 2017. – URL: https://arxiv.org/abs/1707.02692 (request date 04.06.2019).
  33. Alotaibi, A. Deep face liveness detection based on nonlinear diffusion using convolution neural network / A. Alotaibi, A. Mahmood // Signal, Image and Video Processing. – 2017. – Vol. 11, Issue 4. – P. 713-720.
  34. Kim, W. Face liveness detection from a single image via diffusion speed model / W. Kim, S. Suh, J.J. Han // IEEE Transactions on Image Processing. – 2015. – Vol. 24, Is-sue 8. – P. 2456-2465.
  35. Komulainen, J. Complementary countermeasures for detecting scenic face spoofing attacks / J. Komulainen, A. Hadid, M. Pietikinen, A. Anjos, S. Marcel // 6th IEEE International Conference on Biometrics (ICB). – 2013. – P. 1-7.
  36. Chingovska, I. On the effectiveness of local binary patterns in face anti-spoofing / I. Chingovska, A. Anjos, S. Marcel // IEEE International Conference of the Biometrics Special Interest Group (BIOSIG). – 2012. – P. 1-7.
  37. Boulkenafet, Z. OULU-NPU: A mobile face presentation attack database with real-world variations / Z. Boulkenafet, J. Komulainen, L. Li, X. Feng, A. Hadid // 12th IEEE International Conference on Automatic Face Gesture Recognition (FG). – 2017. – P. 612-618.
  38. Han, Y.J. Efficient eye-blinking detection on smartphones: A hybrid approach based on deep learning / Y.J. Han, W. Kim, J.S. Park // Mobile Information Systems. – 2018. – Vol. 2018. – 6929762.

     


© 2009, IPSI RAS
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: ko@smr.ru ; тел: +7 (846) 242-41-24 (ответственный секретарь), +7 (846) 332-56-22 (технический редактор), факс: +7 (846) 332-56-20