Ying Zhang
Roger Zimmermann
Bin Guo
ABSTRACT
Face verification is a trending way to verify someone’s identity in broad applications. But such systems are vulnerable to face spoofing attacks via, for example, a fraudulent copy of a photo, making it necessary to include face liveness detection as an additional safeguard. Among most existing studies, the face liveness detection is realized in a separate machine learning model in addition to the model for face verification. Such a two-model configuration may face challenges when deployed onto platforms with limited computation power and storage (e.g. mobile phone, IoT devices), especially considering each model may have millions of parameters. Inspired by the fact that humans can verify a person’s identity and liveness at a single glance from a face, we develop a novel system, named FaceLivePlus, to learn a single and universal face descriptor for the two tasks (face verification and liveness detection) so that the computational workload and storage space can be halved. To achieve this, we formulate the underlying relationship between the two tasks, and seamlessly embed this relationship in a distance ranking deep model. The model directly works on features rather than classification labels, which makes the system well generalized on unseen data. Extensive experiments show that our average half total error rate (HTER) has at least 15% and 8% improvement from the state-of-the-arts on two benchmark datasets. We anticipate this approach could become a new direction for face authentication.
- Sheng Hua Bao, Min Li, Wei Hong Qian, and Zhong Su. 2017. Secure face authentication with liveness detection for mobile. US Patent 9,684,779.Google Scholar
- Zinelabidine Boulkenafet, Jukka Komulainen, and Abdenour Hadid. 2016. Face spoofing detection using colour texture analysis. IEEE Transactions on Information Forensics and Security 11, 8 (2016), 1818–1830.Google ScholarDigital Library
- Zinelabinde Boulkenafet, Jukka Komulainen, Lei Li, Xiaoyi Feng, and Abdenour Hadid. 2017. OULU-NPU: A mobile face presentation attack database with real-world variations. In FG. 612–618.Google Scholar
- Qiong Cao, Li Shen, Weidi Xie, Omkar M Parkhi, and Andrew Zisserman. 2018. Vggface2: A dataset for recognising faces across pose and age. In FG. 67–74.Google Scholar
- Hakan Cevikalp and Bill Triggs. 2010. Face recognition based on image sets. In CVPR. 2567–2573.Google Scholar
- Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International Conference on Machine Learning. 794–803.Google Scholar
- Ivana Chingovska, André Anjos, and Sébastien Marcel. 2012. On the Effectiveness of Local Binary Patterns in Face Anti-spoofing. IEEE BIOSIG 2012.Google Scholar
- Ivana Chingovska, André Anjos, and Sébastien Marcel. 2012. On the effectiveness of local binary patterns in face anti-spoofing. In BIOSIG. 1–7.Google Scholar
- Ivana Chingovska, Amir Mohammadi, André Anjos, and Sébastien Marcel. 2019. Evaluation Methodologies for Biometric Presentation Attack Detection. In Handbook of Biometric Anti-Spoofing. Springer, 457–480.Google Scholar
- Sumit Chopra, Raia Hadsell, and Yann LeCun. [n.d.]. Learning a similarity metric discriminatively, with application to face verification. In CVPR.Google Scholar
- Tiago de Freitas Pereira, Jukka Komulainen, André Anjos, José Mario De Martino, Abdenour Hadid, Matti Pietikäinen, and Sébastien Marcel. 2014. Face liveness detection using dynamic texture. EURASIP Journal on Image and Video Processing 2014, 1 (2014), 2.Google ScholarCross Ref
- Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. 2019. Arcface: Additive angular margin loss for deep face recognition. In CVPR. 4690–4699.Google Scholar
- Nesli Erdogmus and Sebastien Marcel. 2013. Spoofing in 2D face recognition with 3D masks and anti-spoofing with Kinect. In BTAS. IEEE, 1–6.Google Scholar
- Litong Feng, Lai-Man Po, Yuming Li, Xuyuan Xu, Fang Yuan, Terence Chun-Ho Cheung, and Kwok-Wai Cheung. 2016. Integration of image quality and motion cues for face anti-spoofing: A neural network approach. Journal of Visual Communication and Image Representation 38 (2016), 451–460.Google ScholarDigital Library
- Javier Galbally, Sébastien Marcel, and Julian Fierrez. 2014. Image quality assessment for fake biometric detection: Application to iris, fingerprint, and face recognition. IEEE transactions on image processing 23, 2 (2014), 710–724.Google Scholar
- Shiming Ge, Shengwei Zhao, Xindi Gao, and Jia Li. 2019. Fewer-Shots and Lower-Resolutions: Towards Ultrafast Face Recognition in the Wild. In ACM MM. 229–237.Google Scholar
- Michelle Guo, Albert Haque, De-An Huang, Serena Yeung, and Li Fei-Fei. 2018. Dynamic task prioritization for multitask learning. In ECCV.Google Scholar
- Junlin Hu, Jiwen Lu, and Yap-Peng Tan. 2014. Discriminative deep metric learning for face verification in the wild. In CVPR. 1875–1882.Google Scholar
- Iasonas Kokkinos. 2017. Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6129–6138.Google ScholarCross Ref
- Huafeng Kuang, Rongrong Ji, Hong Liu, Shengchuan Zhang, Xiaoshuai Sun, Feiyue Huang, and Baochang Zhang. 2019. Multi-modal Multi-layer Fusion Network with Average Binary Center Loss for Face Anti-spoofing. In ACM MM. 48–56.Google Scholar
- Chien Eao Lee, Lilei Zheng, Ying Zhang, Vrizlynn LL Thing, and Ying Yu Chu. 2018. Towards building a remote anti-spoofing face authentication system. In TENCON 2018-2018 IEEE Region 10 Conference. IEEE, 0321–0326.Google ScholarCross Ref
- Haoliang Li, Wen Li, Hong Cao, Shiqi Wang, Feiyue Huang, and Alex C Kot. 2018. Unsupervised domain adaptation for face anti-spoofing. IEEE Transactions on Information Forensics and Security 13, 7 (2018), 1794–1809.Google ScholarCross Ref
- Lei Li, Xiaoyi Feng, Zinelabidine Boulkenafet, Zhaoqiang Xia, Mingming Li, and Abdenour Hadid. 2016. An original face anti-spoofing approach using partial convolutional neural network. In IPTA. 1–6.Google Scholar
- Lei Li, Zhaoqiang Xia, Xiaoyue Jiang, Fabio Roli, and Xiaoyi Feng. 2018. Face presentation attack detection in learned color-liked space. arXiv preprint arXiv:1810.13170 (2018).Google Scholar
- Yan Li, Yingjiu Li, Ke Xu, Qiang Yan, and Robert H Deng. 2016. Empirical study of face authentication systems under OSNFD attacks. IEEE Transactions on Dependable and Secure Computing 15, 2 (2016), 231–245.Google ScholarCross Ref
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. 2980–2988.Google ScholarCross Ref
- Jukka Määttä, Abdenour Hadid, and Matti Pietikäinen. 2011. Face spoofing detection from single images using micro-texture analysis. In IJCB. 1–7.Google Scholar
- Zuheng Ming, Junshi Xia, Muhammad Muzzamil Luqman, Jean-Christophe Burie, and Kaixing Zhao. 2019. FaceLiveNet+: A Holistic Networks For Face Authentication Based On Dynamic Multi-task Convolutional Neural Networks. arXiv preprint arXiv:1902.11179 (2019).Google Scholar
- Olivier Moindrot. 2018. Triplet Loss and Online Triplet Mining in TensorFlow. https://omoindrot.github.io/triplet-loss##batch-hard-strategy.Google Scholar
- Gang Pan, Lin Sun, Zhaohui Wu, and Shihong Lao. 2007. Eyeblink-based anti-spoofing in face recognition from a generic webcamera. In ICCV. IEEE, 1–8.Google Scholar
- Norman Poh and Samy Bengio. 2006. Database, protocols and tools for evaluating score-level fusion algorithms in biometric authentication. Pattern Recognition 39, 2 (2006), 223–233.Google ScholarDigital Library
- Yasar Abbas Ur Rehman, Lai-Man Po, Mengyang Liu, Zijie Zou, Weifeng Ou, and Yuzhi Zhao. 2019. Face liveness detection using convolutional-features fusion of real and deep network generated face images. Journal of Visual Communication and Image Representation 59 (2019), 574–582.Google ScholarDigital Library
- Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017).Google Scholar
- Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. Facenet: A unified embedding for face recognition and clustering. In CVPR. 815–823.Google Scholar
- Xiaokang Tu and Yuchun Fang. 2017. Ultra-deep neural network for face anti-spoofing. In International Conference on Neural Information Processing. Springer, 686–695.Google ScholarCross Ref
- Matthew Turk and Alex Pentland. 1991. Face recognition using eigenfaces. In CVPR. 586–587.Google Scholar
- Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li, and Wei Liu. 2018. Cosface: Large margin cosine loss for deep face recognition. In CVPR. 5265–5274.Google Scholar
- Di Wen, Hu Han, and Anil K Jain. 2015. Face spoof detection with image distortion analysis. IEEE Transactions on Information Forensics and Security 10, 4 (2015), 746–761.Google ScholarDigital Library
- Yue Wu, Hongfu Liu, Jun Li, and Yun Fu. 2017. Deep face recognition with center invariant loss. In ACM MM Thematic Workshops. 408–414.Google ScholarDigital Library
- Zhenqi Xu, Shan Li, and Weihong Deng. 2015. Learning temporal features using LSTM-CNN architecture for face anti-spoofing. In ACPR. 141–145.Google Scholar
- Jianwei Yang, Zhen Lei, and Stan Z Li. 2014. Learn convolutional neural network for face anti-spoofing. arXiv preprint arXiv:1408.5601 (2014).Google Scholar
- Yingyuan Yang, Jinyuan Sun, and Linke Guo. 2016. PersonaIA: a lightweight implicit authentication system based on customized user behavior selection. IEEE Transactions on Dependable and Secure Computing 16, 1 (2016), 113–126.Google ScholarDigital Library
- Hao Ye, Weiyuan Shao, Hong Wang, Jianqi Ma, Li Wang, Yingbin Zheng, and Xiangyang Xue. 2016. Face recognition via active annotation and learning. In ACM MM. 1058–1062.Google Scholar
- Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z Li. 2014. Learning face representation from scratch. arXiv preprint arXiv:1411.7923 (2014).Google Scholar
- Xiaowen Ying, Xin Li, and Mooi Choo Chuah. 2018. LiveFace: A Multi-task CNN for Fast Face-Authentication. In ICMLA. 955–960.Google Scholar
- Byungin Yoo, KWAK Youngjun, Jungbae Kim, SON Jinwoo, LEE Changkyo, Chang Kyu Choi, and HAN JaeJoon. 2019. Liveness test method and apparatus. US Patent App. 16/148,587.Google Scholar
- Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, and Yu Qiao. 2016. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters 23, 10 (2016), 1499–1503.Google ScholarCross Ref
- Yan Ke He Zhen-Yu Zhang, Jian and Yong Xu. 2014. A Collaborative Linear Discriminative Representation Classification Method for Face Recognition. In International Conference on Artificial Intelligence and Software Engineering.Google Scholar
- Zhiwei Zhang, Junjie Yan, Sifei Liu, Zhen Lei, Dong Yi, and Stan Z Li. 2012. A face antispoofing database with diverse attacks. In ICB. 26–31.Google Scholar
Index Terms
- FaceLivePlus: A Unified System for Face Liveness Detection and Face Verification
Recommendations
Face Liveness Detection Based on Client Identity Using Siamese Network
Pattern Recognition and Computer VisionAbstractFace liveness detection is an essential prerequisite for face recognition applications. Previous face liveness detection methods usually train a binary classifier to differentiate between a fake face and a real face before face recognition. The ...
2D Pose-Invariant Face Recognition Using Single Frontal-View Face Database
AbstractPersonal identification systems that use face recognition work well for test images with frontal view face, but often fail when the input face is a pose view. Most face databases come from picture ID sources such as passports or driver’s licenses. ...
Face liveness detection using convolutional-features fusion of real and deep network generated face images
Highlights- A frame work for evaluating real-world and DNG images for face liveness detection.
AbstractConventionally, classifiers designed for face liveness detection are trained on real-world images, where real-face images and corresponding face presentation attacks (PA) are very much overlapped. However, a little research has been ...
Comments