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. 智能感知与计算研究中心
Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack

文献类型：期刊论文

作者Luo, Zhengquan1; Wang, Yunlong2; Liu, Nianfeng2; Wang, Zilei1
刊名IET BIOMETRICS
出版日期2022-08-27
页码10
ISSN号2047-4938
DOI10.1049/bme2.12092
通讯作者Wang, Yunlong(yunlongwang@cnpac.ia.ac.cn)
英文摘要Iris presentation attack detection (PAD) is still an unsolved problem mainly due to the various spoof attack strategies and poor generalisation on unseen attackers. In this paper, the merits of both light field (LF) imaging and deep learning (DL) are leveraged to combine 2D texture and 3D geometry features for iris liveness detection. By exploring off-the-shelf deep features of planar-oriented and sequence-oriented deep neural networks (DNNs) on the rendered focal stack, the proposed framework excavates the differences in 3D geometric structure and 2D spatial texture between bona fide and spoofing irises captured by LF cameras. A group of pre-trained DL models are adopted as feature extractor and the parameters of SVM classifiers are optimised on a limited number of samples. Moreover, two-branch feature fusion further strengthens the framework's robustness and reliability against severe motion blur, noise, and other degradation factors. The results of comparative experiments indicate that variants of the proposed framework significantly surpass the PAD methods that take 2D planar images or LF focal stack as input, even recent state-of-the-art (SOTA) methods fined-tuned on the adopted database. Presentation attacks, including printed papers, printed photos, and electronic displays, can be accurately detected without fine-tuning a bulky CNN. In addition, ablation studies validate the effectiveness of fusing geometric structure and spatial texture features. The results of multi-class attack detection experiments also verify the good generalisation ability of the proposed framework on unseen presentation attacks.
资助项目CAAI Huawei MindSpore Open Fund[CAAIXSJLJJ-2021-053A] ; National Natural Science Foundation of China[61906199] ; National Natural Science Foundation of China[62006225] ; National Natural Science Foundation of China[62176025] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA27040700]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000846483600001
出版者WILEY
资助机构CAAI Huawei MindSpore Open Fund ; National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/50062]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Wang, Yunlong
作者单位1.Univ Sci & Technol China, Dept Automat, Hefei, Anhui, Peoples R China
2.Chinese Acad Sci CASIA, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattem Recognit NLPR, Inst Automat, 95 Zhongguancun East St, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Luo, Zhengquan,Wang, Yunlong,Liu, Nianfeng,et al. Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack[J]. IET BIOMETRICS,2022:10.
APA Luo, Zhengquan,Wang, Yunlong,Liu, Nianfeng,&Wang, Zilei.(2022).Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack.IET BIOMETRICS,10.
MLA Luo, Zhengquan,et al."Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack".IET BIOMETRICS (2022):10.

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。