Abstract
Using multi-modal data, such as VIS, IR and Depth, for face anti-spoofing (FAS) is a robust and effective method, because complementary information between different modalities can better against various attacks. However, multi-modal data is difficult to obtain in application scenarios due to high costs, which makes the model trained with multi-modal data unavailable in the testing stage. We define this phenomenon as train-test inconsistency problem, which is ignored by most existing methods. To this end, we propose a novel multi-modal face anti-spoofing framework (GFF), which adopt multi-modal data during training, and only use a single modality during testing to simulate multi-modal input. Specifically, GFF is a two-step framework. In the step I, we adopt the GAN model to fit the face images distribution of different modalities, and learn the transform strategies between different distributions, so as to realize the generation from a single real modality image to other modalities. In the step II, we select the real face images in one modality and the generated images in the other modalities according to actual needs to construct a simulation dataset, which is used for training face anti-spoofing model. The advantage of GFF is that it has achieved a good trade-off between data capture cost and model performance in the real application scenarios. The experimental results show that the method proposed in this paper can effectively overcome the train-test inconsistency problem. On the CASIA-SRUF CeFA dataset, the performance of GFF surpasses the existing single-modality-based methods, and surprisingly surpasses some multi-modality-based methods.
This is a student paper.
This project is supported by the NSFC (62076258).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Due to some of our input are generated rather than real, our model is a multi-modal-like model.
References
Chen, S., Li, W., Yang, H., Huang, D., Wang, Y.: 3D face mask anti-spoofing via deep fusion of dynamic texture and shape clues. In: FG, pp. 314–321 (2020)
Chen, X., Xu, S., Ji, Q., Cao, S.: A dataset and benchmark towards multi-modal face anti-spoofing under surveillance scenarios. IEEE Access 9, 28140–28155 (2021)
Chikontwe, P., Gao, Y., Lee, H.J.: Transformation guided representation GAN for pose invariant face recognition. Multidimension. Syst. Signal Process. 32(2), 633–649 (2021)
Choi, Y., Uh, Y., Yoo, J., Ha, J.: StarGAN v2: diverse image synthesis for multiple domains. In: CVPR, pp. 8185–8194 (2020)
Huang, Z., Chen, S., Zhang, J., Shan, H.: PFA-GAN: progressive face aging with generative adversarial network. IEEE Trans. Inf. Forensics Secur. 16, 2031–2045 (2021)
Jiang, F., Liu, P., Shao, X., Zhou, X.: Face anti-spoofing with generated near-infrared images. Multimedia Tools Appl. 79(29–30), 21299–21323 (2020)
Jiang, F., Liu, P., Zhou, X.: Multilevel fusing paired visible light and near-infrared spectral images for face anti-spoofing. Pattern Recogn. Lett. 128, 30–37 (2019)
Kavitha, P., Vijaya, K.: Fuzzy local ternary pattern and skin texture properties based countermeasure against face spoofing in biometric systems. Comput. Intell. 37(1), 559–577 (2021)
Liu, A., et al.: Cross-ethnicity face anti-spoofing recognition challenge: a review. CoRR (2020)
Liu, A., et al.: CASIA-SURF CeFA: a benchmark for multi-modal cross-ethnicity face anti-spoofing. CoRR abs/2003.05136 (2020)
Luo, M., Cao, J., Ma, X., Zhang, X., He, R.: FA-GAN: face augmentation GAN for deformation-invariant face recognition. IEEE Trans. Inf. Forensics Secur. 16, 2341–2355 (2021)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E.B., Garnett, R. (eds.) NeurIPS, pp. 8024–8035 (2019)
Qin, Y., et al.: Learning meta model for zero-and few-shot face anti-spoofing. In: AAAI (2020)
Shu, X., Tang, H., Huang, S.: Face spoofing detection based on chromatic ED-LBP texture feature. Multimedia Syst. 27(2), 161–176 (2021)
Wang, Q., Fan, H., Sun, G., Ren, W., Tang, Y.: Recurrent generative adversarial network for face completion. IEEE Trans. Multimedia 23, 429–442 (2021)
Wang, Z., et al.: Deep spatial gradient and temporal depth learning for face anti-spoofing. In: CVPR, pp. 5041–5050 (2020)
Yang, Q., Zhu, X., Fwu, J., Ye, Y., You, G., Zhu, Y.: PipeNet: selective modal pipeline of fusion network for multi-modal face anti-spoofing. In: CVPR Workshops, pp. 2739–2747. IEEE (2020)
Yu, Z., Wan, J., Qin, Y., Li, X., Li, S.Z., Zhao, G.: NAS-FAS: static-dynamic central difference network search for face anti-spoofing. IEEE Trans. Pattern Anal. Mach. Intell. 43(9), 3005–3023 (2021). https://doi.org/10.1109/TPAMI.2020.3036338
Yu, Z., Li, X., Niu, X., Shi, J., Zhao, G.: Face anti-spoofing with human material perception. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 557–575. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58571-6_33
Yu, Z., et al.: Multi-modal face anti-spoofing based on central difference networks. In: CVPR Workshops, pp. 2766–2774. IEEE (2020)
Yu, Z., et al.: Searching central difference convolutional networks for face anti-spoofing. In: CVPR (2020)
Zhang, S., et al.: CASIA-SURF: a large-scale multi-modal benchmark for face anti-spoofing. IEEE Trans. Biometrics Behav. Identity Sci. 2(2), 182–193 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, Q., Liao, Z., Huang, Y., Lai, J. (2021). Multi-modal Face Anti-spoofing Based on a Single Image. In: Ma, H., et al. Pattern Recognition and Computer Vision. PRCV 2021. Lecture Notes in Computer Science(), vol 13021. Springer, Cham. https://doi.org/10.1007/978-3-030-88010-1_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-88010-1_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88009-5
Online ISBN: 978-3-030-88010-1
eBook Packages: Computer ScienceComputer Science (R0)