A Domain Generalized Face Anti-Spoofing System Using Domain Adversarial Learning

Ching-Yi Chen; Sin-Ye Jhong; Chih-Hsien Hsia

doi:10.46604/ijeti.2024.13314

Authors

Ching-Yi Chen Department of Information and Telecommunications Engineering, Ming Chuan University, Taoyuan, Taiwan, ROC
Sin-Ye Jhong Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan, ROC
Chih-Hsien Hsia Department of Computer Science and Information Engineering, National Ilan University, Ilan, Taiwan, ROC

DOI:

https://doi.org/10.46604/ijeti.2024.13314

Keywords:

face anti-spoofing, representation learning, adversarial learning algorithms, Grad-CAM

Abstract

This research addresses the enhancement of face anti-spoofing (FAS) in facial recognition systems (FRS) against sophisticated fraudulent activities. Prior methods primarily focus on extracting facial features like color, texture, and dynamic variations, yet these methods struggle to accurately identify common characteristics of forged faces, thereby limiting generalization in practical scenarios. This study aims to propose a novel representation learning framework incorporating adversarial learning algorithms, to segregate features into liveness-specific and domain-specific categories, emphasizing liveness-specific features for FAS advancement. Feature disentanglement is central to this approach, enabling the deep learning models to effectively discern separable latent generating factors, such as identity, liveness, appearance, and texture. This methodology enhances model interpretability, explainability, and generalization. Additionally, Grad-CAM is employed to elucidate the basis for classifications made by the architecture, increasing explainability and trustworthiness. Empirical evaluation across panoply available FAS datasets confirms the superiority, significantly improving performance and robustness over existing technologies.

References

Z. Boulkenafet, J. Komulainen, and A. Hadid, “Face Spoofing Detection Using Colour Texture Analysis,” IEEE Transactions on Information Forensics and Security, vol. 11, no. 8, pp. 1818-1830, August 2016.

U. Muhammad, M. Z. Hoque, M. Oussalah, and J. Laaksonen, “Deep Ensemble Learning With Frame Skipping for Face Anti-Spoofing,” Twelfth International Conference on Image Processing Theory, Tools and Applications, pp. 1-6, October 2023.

Q. Guo, S. Liao, Y. Chen, S. Xiao, and J. Ma, “A Deep Learning Based Approach for 3D Mask Face Anti-Spoofing Enhancement,” 8th International Conference on Computer and Communication Systems, pp. 1-5, April 2023.

N. Nanthini, N. Puviarasan, and P. Aruna, “An Enhanced Face Anti-Spoofing Model Using Color Texture and Corner Feature Based Liveness Detection,” 2nd International Conference on Innovative Practices in Technology and Management, pp. 63-68, February 2022.

K. Karthik and B. R. Katika, “Image Quality Assessment Based Outlier Detection for Face Anti-Spoofing,” 2nd International Conference on Communication Systems, Computing and IT Applications, pp. 72-77, April 2017.

R. Shao, X. Lan, and P. C. Yuen, “Deep Convolutional Dynamic Texture Learning With Adaptive Channel-Discriminability for 3D Mask Face Anti-Spoofing,” IEEE International Joint Conference on Biometrics, pp. 748-755, October 2017.

J. Yang, Z. Lei, and S. Z. Li, “Learn Convolutional Neural Network for Face Anti-Spoofing,” https://doi.org/10.48550/arXiv.1408.5601, August 24, 2014.

L. Li, X. Feng, Z. Boulkenafet, Z. Xia, M. Li, and A. Hadid, “An Original Face Anti-Spoofing Approach Using Partial Convolutional Neural Network,” Sixth International Conference on Image Processing Theory, Tools and Applications, pp. 1-6, December 2016.

R. Shao, X. Lan, J. Li, and P. C. Yuen, “Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10015-10023, June 2019.

Y. Jia, J. Zhang, S. Shan, and X. Chen, “Single-Side Domain Generalization for Face Anti-Spoofing,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8481-8490, June 2020.

H. Li, S. J. Pan, S. Wang, and A. C. Kot, “Domain Generalization With Adversarial Feature Learning,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5400-5409, June 2018.

Z. C. Chen, L. H. Tsao, C. L. Fu, and Y. C. Frank Wang, “Disentangled Representation for Domain Generalized Face Anti-Spoofing,” Graduate Institute of Communication Engineering, National Taiwan University, Bachelor Thesis Award, 2021.

Y. C. Wang, C. Y. Wang, and S. H. Lai, “Disentangled Representation With Dual-Stage Feature Learning for Face Anti-Spoofing,” IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1234-1243, January 2022.

Z. Liu, Z. Feng, Z. Zou, R. Zhang, M. Song, and J. Shen, “Disentangled Representation Based Face Anti-Spoofing,” 25th International Conference on Pattern Recognition, pp. 2017-2024, January 2021.

R. Geirhos, J. H. Jacobsen, C. Michaelis, R. Zemel, W. Brendel, M. Bethge, et al., “Shortcut Learning in Deep Neural Networks,” Nature Machine Intelligence, vol. 2, pp. 665-673, 2020.

Z. Ren, “The Advance of Generative Model and Variational Autoencoder,” IEEE Conference on Telecommunications, Optics and Computer Science, pp. 268-271, December 2022.

K. Sun, Q. Wen, and H. Zhou, “Ganster R-CNN: Occluded Object Detection Network Based on Generative Adversarial Nets and Faster R-CNN,” IEEE Access, vol. 10, pp. 105022-105030, 2022.

H. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, et al., “CosFace: Large Margin Cosine Loss for Deep Face Recognition,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5265-5274, June 2018.

W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song, “SphereFace: Deep Hypersphere Embedding for Face Recognition,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 6738-6746, July 2017.

J. Deng, J. Guo, J. Yang, N. Xue, I. Kotsia, and S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 10_Part_1, pp. 5962-5979, October 2022.

Z. Boulkenafet, J. Komulainen, L. Li, X. Feng, and A. Hadid, “Oulu-NPU: A Mobile Face Presentation Attack Database With Real-World Variations,” 12th IEEE International Conference on Automatic Face & Gesture Recognition, pp. 612-618, May-June 2017.

Z. Zhang, J. Yan, S. Liu, Z. Lei, D. Yi, and S. Z. Li, “A Face Antispoofing Database With Diverse Attacks,” 5th IAPR International Conference on Biometrics, pp. 26-31, March-April 2012.

I. Chingovska, A. Anjos, and S. Marcel, “On the Effectiveness of Local Binary Patterns in Face Anti-Spoofing,” BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group, pp. 1-7, September 2012.

D. Wen, H. Han, and A. K. Jain, “Face Spoof Detection With Image Distortion Analysis,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 4, pp. 746-761, April 2015.

T. de Freitas Pereira, A. Anjos, J. M. De Martino, and S. Marcel, “LBP − TOP Based Countermeasure Against Face Spoofing Attacks,” Computer Vision - ACCV 2012 Workshops: ACCV 2012 International Workshops, pp. 121-132, November 2012.

J. Määttä, A. Hadid, and M. Pietikäinen, “Face Spoofing Detection From Single Images Using Micro-Texture Analysis,” International Joint Conference on Biometrics, pp. 1-7, October 2011.

Y. Liu, A. Jourabloo, and X. Liu, “Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 389-398, June 2018.

K. Duvvuri, S. Chethana, S. S. Charan, V. Srihitha, T. K. Ramesh and K. S. Srikanth, “Grad-CAM for Visualizing Diabetic Retinopathy,” 3rd International Conference for Emerging Technology, pp. 1-4, May 2022.