Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack
Abstract 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 g...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | IET Biometrics |
| Online Access: | https://doi.org/10.1049/bme2.12092 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850208573626253312 |
|---|---|
| author | Zhengquan Luo Yunlong Wang Nianfeng Liu Zilei Wang |
| author_facet | Zhengquan Luo Yunlong Wang Nianfeng Liu Zilei Wang |
| author_sort | Zhengquan Luo |
| collection | DOAJ |
| description | Abstract 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. |
| format | Article |
| id | doaj-art-93f202ce2eb1434d9e7b9e7015d52e18 |
| institution | OA Journals |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-93f202ce2eb1434d9e7b9e7015d52e182025-08-20T02:10:13ZengWileyIET Biometrics2047-49382047-49462022-09-0111542042910.1049/bme2.12092Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stackZhengquan Luo0Yunlong Wang1Nianfeng Liu2Zilei Wang3Department of Automation University of Science and Technology of China Hefei Anhui ChinaCenter for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) Institute of Automation Chinese Academy of Sciences (CASIA) Beijing ChinaCenter for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) Institute of Automation Chinese Academy of Sciences (CASIA) Beijing ChinaDepartment of Automation University of Science and Technology of China Hefei Anhui ChinaAbstract 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.https://doi.org/10.1049/bme2.12092 |
| spellingShingle | Zhengquan Luo Yunlong Wang Nianfeng Liu Zilei Wang Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack IET Biometrics |
| title | Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack |
| title_full | Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack |
| title_fullStr | Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack |
| title_full_unstemmed | Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack |
| title_short | Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack |
| title_sort | combining 2d texture and 3d geometry features for reliable iris presentation attack detection using light field focal stack |
| url | https://doi.org/10.1049/bme2.12092 |
| work_keys_str_mv | AT zhengquanluo combining2dtextureand3dgeometryfeaturesforreliableirispresentationattackdetectionusinglightfieldfocalstack AT yunlongwang combining2dtextureand3dgeometryfeaturesforreliableirispresentationattackdetectionusinglightfieldfocalstack AT nianfengliu combining2dtextureand3dgeometryfeaturesforreliableirispresentationattackdetectionusinglightfieldfocalstack AT zileiwang combining2dtextureand3dgeometryfeaturesforreliableirispresentationattackdetectionusinglightfieldfocalstack |