Abstract
This study introduces a strategy for synthetic image generation aimed at enhancing the detection capability of facial authentication systems (FAS). By employing various digital manipulation techniques, new synthetic fake images were generated using existing datasets. Through experiments and result analysis, the impact of using these new fake samples on improving the detection accuracy of FAS systems was evaluated. The findings demonstrated the effectiveness of synthetic image generation in augmenting the diversity and complexity of the training data. Fine-tuning using the enhanced datasets significantly improved the detection accuracy across the evaluated FAS systems. Nonetheless, the degree of improvement varied among systems, indicating varying susceptibility to specific types of attacks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
References
Cai, R., Li, Z., Wan, R., Li, H., Hu, Y., Kot, A.C.: Learning meta pattern for face anti-spoofing. CoRR abs/2110.06753 (2021). https://arxiv.org/abs/2110.06753
Feng, H., et al.: Learning generalized spoof cues for face anti-spoofing. CoRR abs/2005.03922 (2020). https://arxiv.org/abs/2005.03922
George, A., Marcel, S.: Deep pixel-wise binary supervision for face presentation attack detection. CoRR abs/1907.04047 (2019). http://arxiv.org/abs/1907.04047
George, A., Mostaani, Z., Geissenbuhler, D., Nikisins, O., Anjos, A., Marcel, S.: Biometric face presentation attack detection with multi-channel convolutional neural network. CoRR abs/1909.08848 (2019). http://arxiv.org/abs/1909.08848
Guo, J., Zhu, X., Xiao, J., Lei, Z., Wan, G., Li, S.Z.: Improving face anti-spoofing by 3D virtual synthesis. CoRR abs/1901.00488 (2019). http://arxiv.org/abs/1901.00488
Han, J., Shoeiby, M., Petersson, L., Armin, M.A.: Dual contrastive learning for unsupervised image-to-image translation. CoRR abs/2104.07689 (2021). https://arxiv.org/abs/2104.07689
Hao, H., Pei, M.: Face liveness detection based on client identity using Siamese network. CoRR abs/1903.05369 (2019). http://arxiv.org/abs/1903.05369
Hernandez-Ortega, J., Fiérrez, J., Morales, A., Galbally, J.: Introduction to presentation attack detection in face biometrics and recent advances. CoRR abs/2111.11794 (2021). https://arxiv.org/abs/2111.11794
Huang, C., Huang, J.: A fast HOG descriptor using lookup table and integral image. CoRR abs/1703.06256 (2017). http://arxiv.org/abs/1703.06256
Innovatrics: Liveness Detection for Remote Identity Verification Solutions (2022). https://www.innovatrics.com/digital-onboarding-toolkit/liveness-detection/
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. CoRR abs/1812.04948 (2018). http://arxiv.org/abs/1812.04948
Kortli, Y., Maher, J., Alfalou, A., Atri, M.: A comparative study of CFs, LBP, HOG, SIFT, SURF, and BRIEF for security and face recognition (2018). https://doi.org/10.1088/978-0-7503-1457-2ch13
Liu, A., Tan, Z., Wan, J., Escalera, S., Guo, G., Li, S.Z.: CASIA-SURF CeFA: a benchmark for multi-modal cross-ethnicity face anti-spoofing. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1178–1186. IEEE Computer Society, Los Alamitos (2021). https://doi.org/10.1109/WACV48630.2021.00122, https://doi.ieeecomputersociety.org/10.1109/WACV48630.2021.00122
Liu, A., et al.: Cross-ethnicity face anti-spoofing recognition challenge: a review. CoRR abs/2004.10998 (2020). https://arxiv.org/abs/2004.10998
Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Gool, L.V.: RePaint: inpainting using denoising diffusion probabilistic models. CoRR abs/2201.09865 (2022). https://arxiv.org/abs/2201.09865
Park, T., Efros, A.A., Zhang, R., Zhu, J.: Contrastive learning for unpaired image-to-image translation. CoRR abs/2007.15651 (2020). https://arxiv.org/abs/2007.15651
Rahim, M.A., Azam, M.S., Hossain, N., Islam, M.R.: Face recognition using local binary patterns (LBP). Glob. J. Comput. Sci. Technol. 13, 1–8 (2013)
sarah.merker@iproov.com: Deepfake Statistics & Solutions – Protect Against Deepfakes (2022). https://www.iproov.com/blog/deepfakes-statistics-solutions-biometric-protection
Uricár, M., Krízek, P., Hurych, D., Sobh, I., Yogamani, S.K., Denny, P.: Yes, we GAN: applying adversarial techniques for autonomous driving. CoRR abs/1902.03442 (2019). http://arxiv.org/abs/1902.03442
Verma, R., Kaur, M.R.: Enhanced character recognition using surf feature and neural network technique (2014)
Wan, J., Guo, G., Escalera, S., Escalante, H.J., Li, S.Z.: Multi-modal Face Presentation Attack Detection. Synthesis Lectures on Computer Vision. Morgan & Claypool Publishers (2020)
Wang, M., Deng, W.: Deep face recognition: a survey. CoRR abs/1804.06655 (2018). http://arxiv.org/abs/1804.06655
Yu, Z., Li, X., Niu, X., Shi, J., Zhao, G.: Face anti-spoofing with human material perception. CoRR abs/2007.02157 (2020). https://arxiv.org/abs/2007.02157
Yu, Z., Li, X., Shi, J., Xia, Z., Zhao, G.: Revisiting pixel-wise supervision for face anti-spoofing. CoRR abs/2011.12032 (2020). https://arxiv.org/abs/2011.12032
Yu, Z., Qin, Y., Li, X., Zhao, C., Lei, Z., Zhao, G.: Deep learning for face anti-spoofing: a survey. CoRR abs/2106.14948 (2021). https://arxiv.org/abs/2106.14948
Zhu, J., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. CoRR abs/1703.10593 (2017). http://arxiv.org/abs/1703.10593
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vega, C., Manrique, R. (2024). Enhancing Face Anti-spoofing Systems Through Synthetic Image Generation. In: Florez, H., Leon, M. (eds) Applied Informatics. ICAI 2023. Communications in Computer and Information Science, vol 1874. Springer, Cham. https://doi.org/10.1007/978-3-031-46813-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-46813-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46812-4
Online ISBN: 978-3-031-46813-1
eBook Packages: Computer ScienceComputer Science (R0)