Detección de ataques de presentación facial basado en siamese-LSTM y el análisis del flujo óptico y puntos de referencia facial

Arnold Jair Jimenez Vargas; Rubiel Vargas Cañas; Carlos Alberto Cobos Lozada; Humberto Loaiza Correa

doi:10.24054/rcta.v1i43.2888

Authors

Arnold Jair Jimenez Vargas Universidad del Cauca https://orcid.org/0009-0003-8314-2062
Rubiel Vargas Cañas Universidad del Cauca https://orcid.org/0000-0003-1548-942X
Carlos Alberto Cobos Lozada Universidad del Cauca https://orcid.org/0000-0002-6263-1911
Humberto Loaiza Correa Universidad del Valle https://orcid.org/0000-0001-7206-7333

DOI:

https://doi.org/10.24054/rcta.v1i43.2888

Keywords:

Biometrics, anti-spoofing, Siamese neural network, LSTM network, optical flow, facial landmark points

Abstract

Facial biometrics authentication has become essential in verifying the identity of individuals in online transactions, as classic mechanisms like username and password authentication have proven unreliable due to users often choosing easily memorable passwords. However, advances in model manufacturing with materials such as latex, print quality improvements, and screen resolution enhancements have demanded that fraud detection systems quickly adapt to new conditions. This paper proposes to address the problem of detecting presentation attacks by extracting optical flow and facial landmarks and analyzing them through a Siamese-LSTM network. The proposed model was evaluated using three datasets: Rose-youtu, Replay-attack, and Replay-mobile, and two metrics: HTER and EER

Downloads

Download data is not yet available.

References

S. Jia, G. Guo, Z. Xu, and Q. Wang, “Face presentation attack detection in mobile scenarios: A comprehensive evaluation,” Image and Vision Computing, vol. 93, p. 103826, Jan. 2020, doi: 10.1016/j.imavis.2019.11.004. DOI: https://doi.org/10.1016/j.imavis.2019.11.004

S. Kumar, S. Singh, and J. Kumar, A Comparative Study on Face Spoofing Attacks. 2017. DOI: https://doi.org/10.1109/CCAA.2017.8229961

Y. Xin et al., “A survey of liveness detection methods for face biometric systems,” Sensor Review, vol. 37, no. 3, pp. 346–356, Jul. 2017, doi: 10.1108/SR-08-2015-0136. DOI: https://doi.org/10.1108/SR-08-2015-0136

J. H. Tu, C. W. Rowley, D. M. Luchtenburg, S. L. Brunton, and J. N. Kutz, “On Dynamic Mode Decomposition: Theory and Applications,” Journal of Computational Dynamics, vol. 1, no. 2, pp. 391–421, Dec. 2014, doi: 10.3934/jcd.2014.1.391. DOI: https://doi.org/10.3934/jcd.2014.1.391

L. Li, X. Feng, Z. Xia, X. Jiang, and A. Hadid, “Face spoofing detection with local binary pattern network,” Journal of Visual Communication and Image Representation, vol. 54, pp. 182–192, Jul. 2018, doi: 10.1016/j.jvcir.2018.05.009. DOI: https://doi.org/10.1016/j.jvcir.2018.05.009

Z. Wang et al., “Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing.” arXiv, Mar. 18, 2020. doi: 10.48550/arXiv.2003.08061. DOI: https://doi.org/10.1109/CVPR42600.2020.00509

X. Tu et al., “Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing,” arXiv:1901.05602 [cs], Jan. 2019, Accessed: Nov. 10, 2019. [Online]. Available: http://arxiv.org/abs/1901.05602

V. Ruiz, I. Linares, A. Sanchez, and J. F. Velez, “Off-line handwritten signature verification using compositional synthetic generation of signatures and Siamese Neural Networks,” Neurocomputing, vol. 374, pp. 30–41, Jan. 2020, doi: 10.1016/j.neucom.2019.09.041. DOI: https://doi.org/10.1016/j.neucom.2019.09.041

A. Niknam, H. K. Zare, H. Hosseininasab, and A. Mostafaeipour, “Developing an LSTM model to forecast the monthly water consumption according to the effects of the climatic factors in Yazd, Iran,” Journal of Engineering Research, vol. 11, no. 1, p. 100028, Mar. 2023, doi: 10.1016/j.jer.2023.100028. DOI: https://doi.org/10.1016/j.jer.2023.100028

A. Al Hamoud, A. Hoenig, and K. Roy, “Sentence subjectivity analysis of a political and ideological debate dataset using LSTM and BiLSTM with attention and GRU models,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 10, Part A, pp. 7974–7987, Nov. 2022, doi: 10.1016/j.jksuci.2022.07.014. DOI: https://doi.org/10.1016/j.jksuci.2022.07.014

L. Li, Z. Xia, J. Wu, L. Yang, and H. Han, “Face presentation attack detection based on optical flow and texture analysis,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 4, pp. 1455–1467, Apr. 2022, doi: 10.1016/j.jksuci.2022.02.019. DOI: https://doi.org/10.1016/j.jksuci.2022.02.019

C. Wang, B. Yu, and J. Zhou, “A Learnable Gradient operator for face presentation attack detection,” Pattern Recognition, vol. 135, p. 109146, Mar. 2023, doi: 10.1016/j.patcog.2022.109146. DOI: https://doi.org/10.1016/j.patcog.2022.109146

S. Fatemifar, S. R. Arashloo, M. Awais, and J. Kittler, “Client-specific anomaly detection for face presentation attack detection,” Pattern Recognition, vol. 112, p. 107696, Apr. 2021, doi: 10.1016/j.patcog.2020.107696. DOI: https://doi.org/10.1016/j.patcog.2020.107696

M. Pei, B. Yan, H. Hao, and M. Zhao, “Person-Specific Face Spoofing Detection Based on a Siamese Network,” Pattern Recognition, vol. 135, p. 109148, Mar. 2023, doi: 10.1016/j.patcog.2022.109148. DOI: https://doi.org/10.1016/j.patcog.2022.109148

C. Yuan, Q. Cui, X. Sun, Q. M. J. Wu, and S. Wu, “Chapter Five - Fingerprint liveness detection using an improved CNN with the spatial pyramid pooling structure,” in Advances in Computers, A. R. Hurson and S. Wu, Eds., Elsevier, 2021, pp. 157–193. doi: 10.1016/bs.adcom.2020.10.002. DOI: https://doi.org/10.1016/bs.adcom.2020.10.002

X. Cheng, J. Zhou, X. Zhao, H. Wang, and Y. Li, “A presentation attack detection network based on dynamic convolution and multi-level feature fusion with security and reliability,” Future Generation Computer Systems, Apr. 2023, doi: 10.1016/j.future.2023.04.012. DOI: https://doi.org/10.1016/j.future.2023.04.012

X. Shu, X. Li, X. Zuo, D. Xu, and J. Shi, “Face spoofing detection based on multi-scale color inversion dual-stream convolutional neural network,” Expert Systems with Applications, vol. 224, p. 119988, Aug. 2023, doi: 10.1016/j.eswa.2023.119988. DOI: https://doi.org/10.1016/j.eswa.2023.119988

S. Fatemifar, S. Asadi, M. Awais, A. Akbari, and J. Kittler, “Face spoofing detection ensemble via multistage optimisation and pruning,” Pattern Recognition Letters, vol. 158, pp. 1–8, Jun. 2022, doi: 10.1016/j.patrec.2022.04.006. DOI: https://doi.org/10.1016/j.patrec.2022.04.006

S. R. Arashloo, “Unknown Face Presentation Attack Detection via Localised Learning of Multiple Kernels.” 2022.

“How do Siamese Networks Work in Image Recognition? | Baeldung on Computer Science.” https://www.baeldung.com/cs/siamese-networks (accessed Apr. 09, 2023).

G. He, F. Li, Q. Wang, Z. Bai, and Y. Xu, “A hierarchical sampling based triplet network for fine-grained image classification,” Pattern Recognition, vol. 115, p. 107889, Jul. 2021, doi: 10.1016/j.patcog.2021.107889. DOI: https://doi.org/10.1016/j.patcog.2021.107889