ABSTRACT
In addition to using synthetic samples to deceive and attack biometric systems, they can also be used to enhance algorithmic robustness. This study investigates the impact of synthetic samples on cosmetic contact lens detection, a typical iris classification task that presents a bottleneck problem. By incorporating varying amounts of synthetic images into the training dataset and training multiple classifiers, we analyze the effect of synthetic samples. For iris liveness detection, we propose a novel SACvT network that incorporates spatial local attention to improve the CvT. The SACvT network comprises the CvT as its backbone and a spatial local attention network that generates an attention feature map from the last Token map of the CvT. A Rank loss is designed to train SACvT without requiring attention annotations. We choose two light-weighted networks as comparison methods, including a modified LightCNN and the CvT. Extensive experiments show that adding synthetic samples based on StyleGANv2 for training can improve classification accuracy. While GAN-based data augmentation cannot replace image processing-based data augmentation, it serves as a complementary approach. The proposed SACvT exhibits promising results in liveness detection, particularly on challenging images such as those with imprecise iris localization or heavy occlusion.
- S Bazrafkan, S Thavalengal, and P Corcoran. 2018. An end to end Deep Neural Network for iris segmentation in unconstrained scenarios. Neural Networks 106 (2018), 79–95.Google ScholarDigital Library
- A Brock, J Donahue, and K Simonyan. 2018. Large Scale GAN Training for High Fidelity Natural Image Synthesis. arXiv: 1809.11096.Google Scholar
- N Carion, F Massa, G Synnaeve, N Usunier, A Kirillov, and S Zagoruyko. 2020. End-to-end object detection with transformers. In ECCV. 213—-229.Google Scholar
- Y Choi, M Choiand, M Kim, J Ha, S Kim, and J Choo. 2018. Stargan: Unified Generative Adversarial Networks for Multidomain Image-to-Image Translation. In CVPR. 8789–8797.Google Scholar
- J Daugman. 2008. Demogulation By Complex-valued Wavelets for StochasticC Pattern Recognition. Intl Journal of Wavelets Multiresolution & Information Processing 01, 01 (2008), 1–17.Google ScholarCross Ref
- A Dosovitskiy, L Beyer, A Kolesnikov, D Weissenborn, X Zhai, T Unterthiner, M Dehghani, M Minderer, G Heigold, S Gelly, J Uszkoreit, and N Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv: 2010.11929.Google Scholar
- J Doyle, K Bowyer, and P Flynn. 2013. Variation in accuracy of textured contact lens detection based on sensor and lens pattern. In IBTAS.Google Scholar
- P Esser, R Rombach, and B Ommer. 2020. Taming Transformers for High-Resolution Image Synthesis. arXiv: 2012.09841.Google Scholar
- D Gragnaniello, C Sansone, G Poggi, and L Verdoliva. 2016. Biometric Spoofing Detection by a Domain-Aware Convolutional Neural Network. In Intl Conf. on Signal-Image Technology & Internet-Based Systems. 193–198.Google ScholarCross Ref
- S Hoffman, R Sharma, and A Ross. 2018. Convolutional Neural Networks for Iris Presentation Attack Detection: Toward Cross-Dataset and Cross-Sensor Generalization. In CVPR Workshops. 1701–1708.Google Scholar
- J Zuo, N Schmid, and X Chen. On Generation and Analysis of Synthetic Iris Images. IEEE Trans. on Information Forensics and Security 2, 1 (2007), 77–90.Google ScholarDigital Library
- T Karras, S Laine, and T Aila. 2019. A Style-Based Generator Architecture for Generative Adversarial Networks. In CVPR.Google Scholar
- T Karras, S Laine, M Aittala, J Hellsten, and T Aila. 2020. Analyzing and Improving the Image Quality of StyleGAN. In CVPR. 8107–8116.Google Scholar
- N Kohli, D Yadav, and M Vatsa. 2017. Synthetic Iris Presentation Attack Using iDCGAN. In IJCB. 674—-680.Google Scholar
- L Nigam, B Kumar, and P Gupta. 2015. Robust Contact Lens Detection Using Local Phase Quantization and Binary Gabor Pattern. In Intl Conf. on Computer Analysis of Images and Patterns. 702–714.Google Scholar
- S Makthal and A Ross. 2015. Synthesis of Iris Images Using Markov Random Fields. In European Signal Processing Conf.Google Scholar
- S. Minaee and A. Abdolrashidi. 2018. Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN. arXiv: 1812.04822.Google Scholar
- A Radford, L Metz, and S Chintala. 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434.Google Scholar
- R Raghavendra, K Raja, and C Busch. 2017. ContlensNet: Robust Iris Contact Lens Detection Using Deep Convolutional Neural Networks. In IEEE Winter Conf. on Applications of Computer Vision. 1160–1167.Google Scholar
- S Shah and A Ross. 2006. Generating Synthetic Irises by Feature Agglomeration. In ICIP. 317–320.Google Scholar
- A Singh, V Mistry, D Yadav, and A Nigam. 2017. GHCLNet: A Generalized Hierarchically tuned Contact Lens detection Network. arXiv:1710.05152 [cs.CV]Google Scholar
- Z Sun, H Zhang, T Tan, and J Wang. Iris Image Classification Based on Hierarchical Visual Codebook. IEEE Trans. on Pattern Analysis and Machine Intelligence 36, 6 (2014), 1120–1133.Google ScholarDigital Library
- Z Sun, H Zhang, T Tan, and J Wang. 2014. Iris image classification based on hierarchical visual codebook. IEEE Trans. on Pattern Analysis and Machine Intelligence 36, 6 (2014), 1120–1133.Google ScholarDigital Library
- H Wang, Y Zhu, H Adam, A Yuille, and L Chen. 2020. MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers. arXiv: 2012.00759 (2020).Google Scholar
- Z Wei, T Tan, and Z Sun. 2008. Synthesis of large realistic iris databases using patch-based sampling. In ICPR. 1–4.Google Scholar
- H Wu, B Xiao, N. Codella, M Liu, X Dai, L Yuan, and L Zhang. 2021. CvT: Introducing Convolutions to Vision Transformers. arXiv: 2103.15808.Google Scholar
- X Wu, R He, and Z Sun. 2015. A Lightened CNN for Deep Face Representation. arXiv: 1511.02683.Google Scholar
- D Yadav, N Kohli, J Doyle, R Singh, M Vatsa, and K Bowyer. 2014. Unraveling the Effect of Textured Contact Lenses on Iris Recognition. IEEE Trans. on Information Forensics and Security 9, 5 (2014), 851–862.Google ScholarDigital Library
- S Yadav, C Chen, and A Ross. 2019. Synthesizing Iris Images Using RaSGAN With Application in Presentation Attack Detection. In CVPR Workshops. 2422–2430.Google Scholar
- H Zhang, Y Bai, H Zhang, J Liu, X Li, and Z He. 2020. Local Attention and Global Representation Collaborating for Fine-grained Classification. In ICPR. 10658–10665.Google Scholar
- H Zhang, . Sun, and T Tan. 2010. Contact Lens Detection Based on Weighted LBP. In ICPR. 4279–4282.Google Scholar
- J Zhu, T Park, P Isola, and A Efros. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv: 1703.10593.Google Scholar
Index Terms
- Investigate the Effect of Sample Synthesis on Deep Networks based Iris Liveness Detection
Recommendations
Liveness detection for dorsal hand vein recognition
As the identification technology is developed day by day, so is the counterfeit, and any accreditation system can be tricked. Therefore, a complete biometric identification system is supposed to distinguish between real and fake. Aiming at the liveness ...
A multimodal liveness detection using statistical texture features and spatial analysis
AbstractBiometric authentication can establish a person’s identity from their exclusive features. In general, biometric authentication can vulnerable to spoofing attacks. Spoofing referred to presentation attack to mislead the biometric sensor. An anti-...
Toward Noncooperative Iris Recognition: A Classification Approach Using Multiple Signatures
This paper focus on noncooperative iris recognition, i.e., the capture of iris images at large distances, under less controlled lighting conditions, and without active participation of the subjects. This increases the probability of capturing very ...
Comments