A 3D Mask Presentation Attack Detection Method Based on Polarization Medium Wave Infrared Imaging
Abstract
:1. Introduction
2. Methods
2.1. Polarization MWIR Imaging
2.1.1. Imaging System
2.1.2. Mathematical Model
2.2. Feature Design
3. Experiments
3.1. Data Collection System and Material
3.2. Data Collection and Composition of Dataset
3.3. Results and Analysis
3.3.1. Difference before and after Wearing Masks
3.3.2. PAD Results
3.3.3. Effect of Facial Temperature
- Whether or not the facial temperature is changed, the polarization infrared images of real faces and 3D face masks can maintain the large differences between them compared with the conventional MWIR intensity images.
- After the increase in facial temperature, the difference in conventional MWIR images between the real and fake faces tends to decrease, while the differences in their polarization images remain at a high level. It is easy for an attacker to make the infrared radiation intensity of a 3D mask similar to that of a real face by changing the facial temperature, so as to reduce the detection performance of the PAD method based on conventional MWIR images. However, the results of this experiment show that changes in the facial temperature cannot reduce the detection performance of the PAD method based on the MWIR polarization characteristics of the material surface and gradient amplitude features.
4. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Neslihan, K.; Jean-Luc, D. On the Vulnerability of Face Recognition Systems to Spoofing Mask Attacks. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 26–31 May 2013; pp. 2357–2361. [Google Scholar]
- Shao, R.; Lan, X.; Yuen, P. Joint discriminative learning of deep dynamic textures for 3D mask face anti-spoofing. IEEE Trans. Inf. Forensics Secur. 2019, 14, 923–938. [Google Scholar] [CrossRef]
- Ramachandra, R.; Bush, C. Presentation attack detection methods for face recognition systems: A comprehensive survey. ACM. Comput. Surv. 2017, 50, 8. [Google Scholar] [CrossRef]
- ISO/IEC JTC1 SC37 Biometrics. ISO/IEC 30107-1:2016. Information Technology—Biometric Presentation Attack Detection—Part 1: Framework; International Organization for Standardization, Vernier: Geneva, Switzerland, 2016. [Google Scholar]
- Gurton, K.; Yuffa, A.; Videen, G. Enhanced facial recognition for thermal imagery using polarimetric imaging. Opt. Lett. 2014, 39, 3857–3859. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Song, X.; Zhao, X.; Fang, L.; Lin, T. Discriminative representation combinations for accurate face spoofing detection. Pattern Recogn. 2019, 85, 220–231. [Google Scholar] [CrossRef] [Green Version]
- Wang, Y.; Chen, S.; Li, W.; Huang, D.; Wang, Y. Face anti-spoofing to 3D masks by combining texture and geometry features. Lect. Notes Comput. Sci. 2018, 10996, 399–408. [Google Scholar]
- Tirunagari, S.; Poh, N.; Windridge, D.; Iorliam, A.; Suki, N.; Ho, A. Detection of face spoofing using visual dynamics. IEEE Trans. Inf. Forensics Secur. 2015, 10, 762–777. [Google Scholar] [CrossRef] [Green Version]
- Erdogmus, N.; Marcel, S. Spoofing face recognition with 3D masks. IEEE Trans. Inf. Forensics Secur. 2014, 9, 1084–1097. [Google Scholar] [CrossRef] [Green Version]
- Boulkenafet, Z.; Komulainen, J.; Hadid, A. Face spoofing detection using colour texture analysis. IEEE Trans. Inf. Forensics Secur. 2016, 11, 1818–1830. [Google Scholar] [CrossRef]
- Wen, D.; Han, H.; Jain, A. Face spoof detection with image distortion analysis. IEEE Trans. Inf. Forensics Secur. 2015, 10, 746–761. [Google Scholar] [CrossRef]
- Agarwal, A.; Yadav, D.; Kohli, N.; Singh, R.; Vatsa, M.; Noore, A. Face Presentation Attack with Latex Masks in Multispectral Videos. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition Workships, Honolulu, HI, USA, 21–26 July 2017; pp. 275–283. [Google Scholar]
- Bharadwaj, S.; Dhamecha, T.; Vatsa, M.; Singh, R. Computationally Efficient Face Spoofing Detection with Motion Magnification. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition Workships, Portland, OR, USA, 23–28 June 2013; pp. 105–110. [Google Scholar]
- Liu, S.; Yuen, P.; Zhang, S.; Zhao, G. 3D mask face anti-spoofing with remote photoplethysmography. Lect. Notes Comput. Sci. 2016, 9911, 85–100. [Google Scholar]
- Abd, A.; Wei, H.; Ferryman, J. Face Anti-Spoofing Countermeasure: Efficient 2D Materials Classification Using Polarization Imaging. In Proceedings of the IEEE International Workshop on Biometrics and Forensics, Coventry, UK, 4–5 April 2017. [Google Scholar]
- Zaliha, A.; Wei, H. Polarization Imaging for Face Spoofing Detection: Identification of Black Ethnical Group. In Proceedings of the IEEE International Conference on Computational Approach in Smart Systems Design and Applications, Kuching, Malaysia, 15–17 August 2018. [Google Scholar]
- Sun, X.; Huang, L.; Liu, C. Multispectral face spoofing detection using VIS–NIR imaging correlation. Int. J. Wavelets Multiresolut. 2018, 16. [Google Scholar] [CrossRef]
- Wang, Y.; Hao, X.; Hou, Y.; Guo, C. A New Multispectral Method for Face Liveness Detection. In Proceedings of the Second IAPR Asian Conference on Pattern Recognition, Naha, Japan, 5–8 November 2013; pp. 922–926. [Google Scholar]
- Liu, J.; Kumar, A. Detecting Presentation Attacks from 3D Face Masks under Multispectral Imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA, 18–22 June 2018; pp. 47–52. [Google Scholar]
- Krizhevsky, A.; Sutskever, I.; Hinton, G. ImageNet Classification with Deep Convolutional Neural Networks; NIPS. Curran Associates Inc.: New York, NY, USA, 2012; Volume 60, pp. 84–90. [Google Scholar]
- Kotwal, K.; Bhattacharjee, S.; Marcel, S. Multispectral Deep Embeddings as a Countermeasure to Custom Silicone Mask Presentation Attacks. IEEE Trans. Biom. Behav. Identity Sci. 2019, 1, 238–251. [Google Scholar] [CrossRef]
- Tan, X.; Li, Y.; Liu, J.; Jiang, L. Face liveness detection from a single image with sparse low rank bilinear discriminative model. Lect. Notes Comput. Sci. 2010, 6316, 504–517. [Google Scholar]
- Bhattacharjee, S.; Mohammadi, A.; Marcel, S. Spoofing Deep Face Recognition with Custom Silicone Masks. In Proceedings of the IEEE Conference on Biometrics Theory, Applications and Systems, Redondo Beach, CA, USA, 22–25 October 2018. [Google Scholar]
- Bhattacharjee, S.; Marcel, S. What You Can’t See Can Help You—Extended Range Imaging for 3D-Mask Presentation Attacks. In Proceedings of the IEEE Conference on Biometrics Special Interest Group, Darmstadt, Germany, 20–22 September 2017; pp. 1–8. [Google Scholar]
- Liu, J.; Zhang, P.; Xiao, R.; Hu, H.; Zhou, L. Image fusion algorithm at pixel level of polarization infrared image. Infrared Laser Eng. 2007, 36, 286–288. [Google Scholar]
- Cremer, F. Infrared polarization measurements and modeling applied to surface-laid antipersonnel landmines. Opt. Eng. 2002, 41, 1021–1032. [Google Scholar]
- Clerk, C.D. The physical basis of polarized emission. Phys. Bull. 1962, 13, 245. [Google Scholar] [CrossRef]
- Flynn, D.; Alexander, C. Polarized surface scattering expressed in terms of a bidirectional reflectance distribution function matrix. Opt. Eng. 1995, 34, 1646–1650. [Google Scholar]
- Gurton, K.; Dahmani, R. Effect of surface roughness and complex indices of refraction on polarized thermal emission. App. Opt. 2005, 44, 5361–5367. [Google Scholar] [CrossRef]
- George, A.; Mostaani, Z.; Geissenbuhler, D.; Nikisins, O.; Anjos, A.; Marcel, S. Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network. IEEE Trans. Inf. Forensics Secur. 2020, 15, 42–55. [Google Scholar] [CrossRef] [Green Version]
- Kurimoto, M.; Azman, M.; Kin, R.; Murakami, Y.; Nagao, M. Influence of Surface Roughness on Hydrophobic Stability of Silicone Rubber Composites in Dynamic Drop Test. In Proceedings of the IEEE 10th Conference on the Properties and Applications of Dielectric Materials, Bangalore, India, 24–28 July 2012. [Google Scholar]
- Liu, C.; Gui, D.; Yu, S.; Chen, W.; Zong, Y. The preparation and characterization of high refractive index and heat-resistant silicone nanocomposites. In Proceedings of the IEEE 17th Conference on Electronic Packaging Technology, Wuhan, China, 16–19 August 2016; pp. 716–720. [Google Scholar]
- Zhong, X.; Wen, X.; Zhu, D. Lookup-table-based inverse model for human skin reflectance spectroscopy: Two-layered Monte Carlo simulations and experiments. Opt. Express 2014, 22, 1852–1864. [Google Scholar] [CrossRef]
- Li, L.; Correia, P.; Hadid, A. Face recognition under spoofing attacks: Countermeasures and research directions. IET Biom. 2018, 7, 3–14. [Google Scholar] [CrossRef]
Data | Type | Gender | Quantity |
---|---|---|---|
Conventional MWIR Images | Real | Male | 52 |
Female | 18 | ||
Fake | Male | 96 | |
Female | 17 | ||
Polarization MWIR Images | Real | Male | 44 |
Female | 19 | ||
Fake | Male | 91 | |
Female | 15 |
Database | Conventional MWIR Images | Polarization MWIR Images | |
---|---|---|---|
Metrics (%) | |||
Accuracy | 93.73 | 95.08 | |
Recall | 93.67 | 95.67 | |
Precision | 95.33 | 96.83 | |
APCER | 4.76 | 5.56 | |
BPCER | 6.28 | 4.34 | |
ACER | 5.52 | 4.95 |
Accuracy | Recall | Precision | ACER | |
---|---|---|---|---|
Mean | 93.73 | 93.67 | 95.33 | 5.52 |
Standard Deviation | 4.1304 | 3.4983 | 5.2915 | 4.0242 |
Accuracy | Recall | Precision | ACER | |
---|---|---|---|---|
Mean | 95.08 | 95.67 | 96.83 | 4.95 |
Standard Deviation | 2.4063 | 3.4983 | 4.855 | 3.4407 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sun, P.; Zeng, D.; Li, X.; Yang, L.; Li, L.; Chen, Z.; Chen, F. A 3D Mask Presentation Attack Detection Method Based on Polarization Medium Wave Infrared Imaging. Symmetry 2020, 12, 376. https://doi.org/10.3390/sym12030376
Sun P, Zeng D, Li X, Yang L, Li L, Chen Z, Chen F. A 3D Mask Presentation Attack Detection Method Based on Polarization Medium Wave Infrared Imaging. Symmetry. 2020; 12(3):376. https://doi.org/10.3390/sym12030376
Chicago/Turabian StyleSun, Pengcheng, Dan Zeng, Xiaoyan Li, Lin Yang, Liyuan Li, Zhouxia Chen, and Fansheng Chen. 2020. "A 3D Mask Presentation Attack Detection Method Based on Polarization Medium Wave Infrared Imaging" Symmetry 12, no. 3: 376. https://doi.org/10.3390/sym12030376