中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Polarized Image Translation From Nonpolarized Cameras for Multimodal Face Anti-Spoofing

文献类型：期刊论文

作者Tian, Yu2,3; Huang, Yalin3; Zhang, Kunbo3,4; Liu, Yue1; Sun, Zhenan3,4
刊名IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
出版日期2023
卷号18页码:5651-5664
关键词Face recognition Faces Feature extraction Imaging Three-dimensional displays Robustness Costs Face antispoofing image translation polarization multimodal
ISSN号1556-6013
DOI10.1109/TIFS.2023.3310348
通讯作者Zhang, Kunbo(kunbo.zhang@ia.ac.cn) ; Liu, Yue(liuyue@bit.edu.cn)
英文摘要In face antispoofing, it is desirable to have multimodal images to demonstrate liveness cues from various perspectives. However, in most face recognition scenarios, only a single modality, namely visible lighting (VIS) facial images is available. This paper first investigates the possibility of generating polarized (Polar) images from VIS cameras without changing the existing recognition devices to improve the accuracy and robustness of Presentation Attack Detection (PAD) in face biometrics. A novel multimodal face antispoofing framework is proposed based on the machine-learning relationship between VIS and Polar images of genuine faces. Specifically, a dual-modal central differential convolutional network (CDCN) is developed to capture the inherent spoofing features between the VIS and the generated Polar modalities. Quantitative and qualitative experimental results show that our proposed framework not only generates realistic Polar face images but also improves the state-of-the-art face anti-spoofing results on the VIS modal database (i.e. CASIA-SURF). Moreover, a polar face database, CASIA-Polar, has been constructed and will be shared with the public at https://biometrics.idealtest.org to inspire future applications within the biometric anti-spoofing field.
资助项目National Natural Science Foundation of China[62071468] ; National Natural Science Foundation of China[62276263] ; National Natural Science Foundation of China[62006225] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA27040202]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001070669000005
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/53155]  
专题多模态人工智能系统全国重点实验室
通讯作者Zhang, Kunbo; Liu, Yue
作者单位1.Beijing Inst Technol, Sch Opt & Photon, Beijing 100081, Peoples R China
2.Beijing Inst Technol, Sch Opt & Photon, Beijing 100081, Peoples R China
3.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
推荐引用方式
GB/T 7714		 Tian, Yu,Huang, Yalin,Zhang, Kunbo,et al. Polarized Image Translation From Nonpolarized Cameras for Multimodal Face Anti-Spoofing[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2023,18:5651-5664.
APA Tian, Yu,Huang, Yalin,Zhang, Kunbo,Liu, Yue,&Sun, Zhenan.(2023).Polarized Image Translation From Nonpolarized Cameras for Multimodal Face Anti-Spoofing.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,18,5651-5664.
MLA Tian, Yu,et al."Polarized Image Translation From Nonpolarized Cameras for Multimodal Face Anti-Spoofing".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 18(2023):5651-5664.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。