Abstract
Current face spoof detection schemes mainly rely on physiological cues such as eye blinking, mouth movements, and micro-expression changes, or textural attributes of the face images [9]. But none of these methods represent a viable mechanism for makeup-induced spoofing, especially since makeup has been widely used. Compared with face alteration techniques such as plastic surgery, makeup is non-permanent and cost efficient, which makes makeup-induced spoofing become a realistic threat to the integrity of a face recognition system. To solve this problem, we propose a generative model to construct spoofing face images (confusing face images) for improving the accuracy and robustness of automatic face recognition. Our network structure is composed of two separate parts, with one using inter-attention mechanism to obtain interested face region, and another using intra-attention to translate imitation style with preserving imitation style-excluding details. These two attention mechanisms can precisely learn imitation style, where inter-attention pays more attention to imitation regions of image and intra-attention learns face attributes with long distance in image. To effectively discriminate generated images, we introduce an imitation style discriminator. Our model (SPGAN) generates face images that transfer the imitation style from target to subject image and preserve the imitation-excluding features. Experimental results demonstrate the performance of our model in improving quality of imitated face images.
- Andre Anjos and Sebastien Marcel. 2011. Counter-measures to photo attacks in face recognition: A public database and a bas. In IJCB. 1–7. Google Scholar
Digital Library
- Martin Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein GAN. In ICML. DOI:https://doi.org/arXiv:1701.07875Google Scholar
- Konstantinos Bousmalis, Nathan Silberman, David Dohan, Dumitru Erhan, and Dilip Krishnan. 2017. Unsupervised pixel-level domain adaptation with generative adversarial networks. In CVPR. DOI:https://doi.org/10.1109/CVPR.2017.18Google Scholar
- Huiwen Chang, Jingwan Lu, Fisher Yu, and Adam Finkelstein. 2018. PairedCycleGAN asymmetric style transfer for applying and removing makeup. In CVPR. 40–48. DOI:https://doi.org/10.1109/CVPR.2018.00012Google Scholar
- Tong Che, Yanran Li, Athul Paul Jacob, Yoshua Bengio, and Wenjie Li. 2017. Mode regularized generative adversarial networks. In ICLR. DOI:https://doi.org/arXiv:1612.02136Google Scholar
- Cunjian Chen, Antitza Dantcheva, and Arun Ross. 2016. An ensemble of patch-based subspaces for makeup-robust face recognition. Inf. Fusion 32, 32 (2016), 80–92. DOI:https://doi.org/10.1016/j.inffus.2015.09.005 Google Scholar
Digital Library
- Li Chen, Kun Zhou, and Stephen Lin. 2015. Simulating makeup through physics-based manipulation of intrinsic image layers. In CVPR.Google Scholar
- Liang Chieh Chen, George Papandreou, Iasonas Kokkinos, and Kevin Murphy. 2018. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 4 (2018), 834–848. DOI:https://doi.org/10.1109/TPAMI.2017.2699184Google Scholar
Cross Ref
- WenTing Chen, Xinpeng Xie, Xi Jia, and Linlin Shen. 2018. Texture deformation based generative adversarial networks for face editing. ArXiv Preprint ArXiv:1812.09832 (2018).Google Scholar
- Jianpeng Cheng, Dong Li, and Mirella Lapata. 2016. Long short-term memory-networks for machine reading. In EMNLP. 551–561. DOI:https://doi.org/10.18653/v1/D16-1053Google Scholar
- Songtao Ding, Shiru Qu, Yuling Xi, and Shaohua Wan. 2019. Stimulus-driven and concept-driven analysis for image caption generation. Neurocomputing (2019), 520–530. DOI:https://doi.org/10.1016/j.neucom.2019.04.095Google Scholar
- Harshala Gammulle, Tharindu Fernando, Simon Denman, Sridha Sridharan, and Clinton Fookes. 2019. Coupled generative adversarial network for continuous fine-grained action segmentation. In WACV. 200–209. DOI:https://doi.org/10.1109/wacv.2019.00027Google Scholar
- Zan Gao, Yinming Li, and Shaohua Wan. 2020. Exploring deep learning for view-based 3D model retrieval. ACM Trans. Multimedia Comput. Commun. Applic. 16, 1 (2020), 1–21. DOI:https://doi.org/10.1145/3377876 Google Scholar
Digital Library
- Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron Courville. 2017. Improved training of Wasserstein GANs. In NIPS. 5769–5779. Google Scholar
Digital Library
- Dong Hao, Neekhara Paarth, and Wu Chao. 2017. Unsupervised image-to-image translation with generative adversarial networks. arXiv:CVPR (2017). DOI:https://doi.org/arXiv:1701.02676Google Scholar
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML. 448–456. Google Scholar
Digital Library
- T. Darrell, J. Long, and E. Shelhamer. 2015. Fully convolutional networks for semantic segmentation. In CVPR. 3431–3440.Google Scholar
- Justin Johnson, Alexandre Alahi, and Li Fei Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. In ECCV. 694–711. DOI:https://doi.org/10.1007/978-3-319-46475-6_43Google Scholar
- Zhu Jun Yan, Park Taesung, and Isola Phillip. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In ICCV. 2242–2251. DOI:https://doi.org/10.1109/iccv.2017.244Google Scholar
- Mohammad Ahangar Kiasari, Dennis Singh Moirangthem, and Minho Lee. 2018. Coupled generative adversarial stacked auto-encoder: CoGASA. Neural Netw. 100 (2018), 1–9. DOI:https://doi.org/10.1016/j.neunet.2018.01.002Google Scholar
Cross Ref
- Olga Komarova. 2016. A neural algorithm of artistic style. J. Vision 16, 12 (2016), 326–326. DOI:https://doi.org/10.1167/16.12.326Google Scholar
Cross Ref
- Guillaume Lample, Neil Zeghidour, Nicolas Usunier, Antoine Bordes, Ludovic Denoyer, and Marc’Aurelio Ranzato. 2017. Fader networks manipulating images by sliding attributes. In NIPS. 5967–5976. Google Scholar
Digital Library
- Anders Boesen Lindbo Larsen, Søren Kaae Sønderby, Hugo Larochelle, and Ole Winther. 2016. Autoencoding beyond pixels using a learned similarity metric. In ICML. 1558–1566. Google Scholar
Digital Library
- Christian Ledig, Lucas Theis, and Huszar. 2017. Photo-realistic single image super-resolution using a generative adversarial network. In CVPR. 105–114. DOI:https://doi.org/10.1109/CVPR.2017.19Google Scholar
- Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, and Zehan Wang. 2017. Photo-realistic single image super-resolution using a generative adversarial network. In CVPR. 105–114. DOI:https://doi.org/10.1109/CVPR.2017.19Google Scholar
- Lingzhi Li, Jianmin Bao, Yang Hao, Dong Chen, and Fang Wen. 2019. FaceShifter: Towards high fidelity and occlusion aware face swapping. In CVPR.Google Scholar
- Minjun Li, Haozhi Huang, Lin Ma, Wei Liu, Tong Zhang, and Yu-Gang Jiang. 2018. Unsupervised image-to-image translation with stacked cycle-consistent adversarial networks. In ECCV. 184–199. DOI:https://doi.org/10.1007/978-3-030-01240-3_12Google Scholar
- Mu Li, Wangmeng Zuo, and David Zhang. 2016. Convolutional network for attribute-driven and identity-preserving human face generation. Preprint arXiv 1608.06434 (2016).Google Scholar
- Mu Li, Wangmeng Zuo, and David Zhang. 2016. Deep identity aware transfer of facial attributes. Preprint arXiv 1610.05586 (2016).Google Scholar
- Zhouhan Lin, Minwei Feng, Cicero Nogueira Dos Santos, Yu Mo, and Yoshua Bengio. 2017. A structured self-attentive sentence embedding. Preprint arXiv:1703.03130 (2017).Google Scholar
- Xiaowei Liu, Kenli Li, and Keqin Li. 2019. Attentive semantic and perceptual faces completion using self-attention generative adversarial networks. Neural Proc. Lett. (2019). DOI:https://doi.org/10.1007/s11063-019-10080-2Google Scholar
- Chen Long, Hanwang Zhang, Jun Xiao, Liqiang Nie, and Tat Seng Chua. 2017. SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning. In CVPR. DOI:https://doi.org/10.1109/CVPR.2017.667Google Scholar
- Xiaofeng Mao, Shuhui Wang, Liying Zheng, and Qingming Huang. 2018. Semantic invariant cross-domain image generation with generative adversarial networks [J]. Neurocomputing 293, 7 (2018), 55--63.Google Scholar
Cross Ref
- Luke Metz, Ben Poole, David Pfau, and Jascha Sohl-Dickstein. 2017. Unrolled generative adversarial networks. In ICLR. DOI:https://doi.org/arXiv:1611.02163Google Scholar
- Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. Preprint arXiv 1411.1784 (2014).Google Scholar
- Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida. 2018. Spectral normalization for generative adversarial networks. Preprint ArXiv (2018). DOI:https://doi.org/arXiv:1802.05957Google Scholar
- Thomas Brox, Olaf Ronneberger, and Philipp Fischer. 2015. U-Net: Convolutional networks for biomedical image segmentation. In MICCAI.Google Scholar
- Andrew Zisserman, Omkar M. Parkhi, and Andrea Vedaldi. 2015. Deep face recognition. In BMVC.Google Scholar
- Ankur P. Parikh, Oscar Tckstrm, Dipanjan Das, and Jakob Uszkoreit. 2016. A decomposable attention model for natural language inference. In EMNLP. 2249–2255. DOI:https://doi.org/10.18653/v1/D16-1244Google Scholar
- Keyurkumar Patel, Hu Han, and Anil K. Jain. 2016. Secure face unlock: Spoof detection on smartphones. IEEE Trans. Inf. Forens. Secur. 11, 10 (2016), 2268–2283. DOI:https://doi.org/10.1109/TIFS.2016.2578288 Google Scholar
Digital Library
- Romain Paulus, Caiming Xiong, and Richard Socher. 2017. A deep reinforced model for abstractive summarization. ArXiv Preprint ArXiv:1705.04304 (2017).Google Scholar
- Guim Perarnau, Joost van de Weijer, Bogdan Raducanu, and Jose M. Álvarez 2016. Invertible conditional GANs for image editing. arXiv preprint arXiv 1611.06355 (2016).Google Scholar
- Albert Pumarola, Antonio Agudo, Aleix M. Martinez, Alberto Sanfeliu, and Francesc Moreno-Noguer. 2018. GANimation: Anatomically-aware facial animation from a single image. In ECCV. 835–851. DOI:https://doi.org/10.1007/978-3-030-01249-6_50Google Scholar
- Weichao Qiu and Alan Yuille. 2016. UnrealCV: Connecting computer vision to unreal engine. In ECCV. 909–916. DOI:https://doi.org/10.1007/978-3-319-49409-8_75Google Scholar
- Alec Radford, Luke Metz, and Soumith Chintala. 2016. Unsupervised representation learning with deep convolutional generative adversarial networks. Preprint ArXiv. DOI:https://doi.org/arXiv:1511.06434Google Scholar
- Stephan R. Richter, Vibhav Vineet, Stefan Roth, and Vladlen Koltun. 2016. Playing for data: Ground truth from computer games. In ECCV. 102–118. DOI:https://doi.org/10.1007/978-3-319-46475-6_7Google Scholar
- Shao Rui, Xiangyuan Lan, Jiawei Li, and Yuen Pong. 2019. Multi-adversarial discriminative deep domain generalization for face presentation attack detection. In CVPR. 10023–10031.Google Scholar
- Andrei A. Rusu, Matej Vecerik, Thomas Rothorl, Nicolas Heess, Razvan Pascanu, and Raia Hadsell. 2016. Sim-to-real robot learning from pixels with progressive nets. Preprint arXiv:1809.07480 (2016).Google Scholar
- Tim Salimans, Han Zhang, Alec Radford, and Dimitris Metaxas. 2018. Improving GANs using optimal transport. In ICLR. DOI:https://arxiv.org/abs/1803.05573.Google Scholar
- Mathew Salvaris, Danielle Dean, and Wee Hyong Tok. 2018. Generative adversarial networks. Preprint arXiv 1406.2661 (2018).Google Scholar
- Wei Shen and Rujie Liu. 2017. Learning residual images for face attribute manipulation. In CVPR. 1225–1233. DOI:https://doi.org/10.1109/cvpr.2017.135Google Scholar
- Casper Kaae Sonderby, Jose Caballero, Lucas Theis, and Wenzhe Shi. 2017. Amortised MAP inference for image super-resolution. In ICLR.Google Scholar
- C. Dong, T. Li, R. Qian. 2018. BeautyGAN: Instrance-level facial makeup transfer with deep generative adversarial network. In MM. 645–653. Google Scholar
Digital Library
- Dickson Tong, Chi Keung Tang, Michael S. Brown, and Ying Qing Xu. 2008. Example-based cosmetic transfer. Cosmet. Toilet.211–218. DOI:https://doi.org/10.1109/PG.2007.31 Google Scholar
Digital Library
- Eric Tzeng, Coline Devin, Judy Hoffman, Chelsea Finn, and Xingchao Peng. 2016. Towards adapting deep visuomotor representations from simulated to real environments. arXiv preprint arXiv 1511.07111 (2016).Google Scholar
- Paul Upchurch, Jacob Gardner, Geoff Pleiss, Robert Pless, Noah Snavely, Kavita Bala, and Kilian Weinberger. 2017. Deep feature interpolation for image content changes. In CVPR. 6090–6099. DOI:https://doi.org/10.1109/CVPR.2017.645Google Scholar
- Shaohua Wan, Yu Xia, Lianyong Qi, Yee Hong Yang, and Mohammed Atiquzzaman. 2020. Automated colorization of a grayscale image with seed points propagation. IEEE Trans. Multimedia 99 (2020), 1–1. DOI:https://doi.org/10.1109/TMM.2020.2976573Google Scholar
- Shuyang Wang and Fu Yun. 2016. Face behind makeup. In AAAI. Google Scholar
Digital Library
- E. Kolve, Y. Zhu, and R. Mottaghi. 2017. Target-driven visual navigation in indoor scenes using deep reinforcement learning. In ICRA. 3357–3364. DOI:https://doi.org/10.1109/ICRA.2017.7989381Google Scholar
- Junichi Yamagishi, Tomi H. Kinnunen, and Nicholas Evans. 2017. Introduction to the issue on spoofing and countermeasures for automatic speaker verification. IEEE J. Select. Topics Sig. Proc. 11, 4 (2017), 585–587. DOI:https://doi.org/10.1109/JSTSP.2017.2698143Google Scholar
Cross Ref
- Donggeun Yoo, Namil Kim, Sunggyun Park, Anthony S. Paek, and In So Kweon. 2016. Pixel-level domain transfer. In ECCV. 517–532. DOI:https://doi.org/10.1007/978-3-319-46484-8_31Google Scholar
- Munyoung Kim Yunjey Choi, Minje Choi, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. 2018. StarGAN:Unified generative adversarial networks for multidomain image-to-image translation. In CVPR. 8789–8797.Google Scholar
- H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena. 2019. Self-attention generative adversarial networks. In ICML. 7354–7363.Google Scholar
- Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, and Dimitris Metaxas. 2017. StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks. In ICCV. 5908–5916.Google Scholar
- Richard Zhang, Phillip Isola, and Alexei A. Efros. 2016. Colorful image colorization. In ECCV. 649–666. DOI:https://doi.org/10.1007/978-3-319-46487-9_40Google Scholar
- Junbo Zhao, Michael Mathieu, and Yann Lecun. 2016. Energy-based generative adversarial network. Preprint ArXiv (2016).Google Scholar
- Shuchang Zhou, Taihong Xiao, Yi Yang, Dieqiao Feng, Qinyao He, and Weiran He. 2017. GeneGAN: Learning object transfiguration and attribute subspace from unpaired data. Preprint arXiv 1705.04932 (2017).Google Scholar
- Jun Yan Zhu, Taesung Park, and Phillip Isola. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In ICCV. 2242–2251. DOI:https://doi.org/10.1109/iccv.2017.244Google Scholar
- Jun Yan Zhu, Philipp Krähenbühl, Eli Shechtman, and Alexei A. Efros. 2016. Generative visual manipulation on the natural image manifold. In ECCV. DOI:https://doi.org/10.1007/978-3-319-46454-1_36Google Scholar
Index Terms
SPGAN: Face Forgery Using Spoofing Generative Adversarial Networks
Recommendations
Latent Spatial Features Based on Generative Adversarial Networks for Face Anti-spoofing
Biometric RecognitionAbstractWith the wide deployment of the face recognition system, many face attacks, such as print attack, video attack and 3D face mask, have emerged. Face anti-spoofing is very important to protect face recognition system from attack. This paper proposes ...
Person-Specific Face Spoofing Detection Based on a Siamese Network
Highlights- Employment of client identity information for face liveness detection
- A siamese ...
AbstractFace spoofing detection is an essential prerequisite for face recognition applications. Previous face spoofing detection methods usually trained a binary classifier to classify the input face as a spoof face or a real face before face ...
FH-GAN: Face Hallucination and Recognition Using Generative Adversarial Network
Neural Information ProcessingAbstractThere are many factors affecting visual face recognition, such as low resolution images, aging, illumination and pose variance, etc. One of the most important problem is low resolution face images which can result in bad performance on face ...






Comments