Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision Fusion
Fingermarks play an important role in document identification. At the same time, fingermarks on paper documents are often accompanied by signatures and background text, which introduce noise to the original fingermark textures and increase the difficulty of detection. A signed fingermark detection m...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/14/5/1998 |
_version_ | 1797264781690798080 |
---|---|
author | Yongliang Zhang Zihan Zhou Jiahang Wang Zipeng Chen |
author_facet | Yongliang Zhang Zihan Zhou Jiahang Wang Zipeng Chen |
author_sort | Yongliang Zhang |
collection | DOAJ |
description | Fingermarks play an important role in document identification. At the same time, fingermarks on paper documents are often accompanied by signatures and background text, which introduce noise to the original fingermark textures and increase the difficulty of detection. A signed fingermark detection method based on deep residual networks and a decision-level fusion strategy was proposed to defend against spoofing attacks from fake fingermarks. Firstly, the multi-scale structure was introduced in the residual module, which improved the network’s depth and breadth without increasing the parameters. Then, the multi-probability label strategy was refined and employed to enhance the local encoding ability of the feature extraction. A score fusion strategy was designed, with weights allocated based on the difference in signed interference levels of local image blocks. Finally, a model fusion strategy based on evidence theory was suggested, which improved detection accuracy by leveraging complementarity between models. A large-scale fingermark database was established, which included real fingermarks made from real fingers and fake fingermarks made from various materials, and this was divided into two sub databases: signed and unsigned. The experimental results show that the proposed method achieves 96.16% accuracy based on the fingerprint dataset of the global liveness detection competition called LivDet2017 and achieves 99.30% accuracy based on the signed fingermark database, while it has good resistance to spoofing attacks from unknown materials. |
first_indexed | 2024-04-25T00:34:22Z |
format | Article |
id | doaj.art-70710fd62f8d454e9df1c2043ec96731 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-04-25T00:34:22Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-70710fd62f8d454e9df1c2043ec967312024-03-12T16:39:45ZengMDPI AGApplied Sciences2076-34172024-02-01145199810.3390/app14051998Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision FusionYongliang Zhang0Zihan Zhou1Jiahang Wang2Zipeng Chen3College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaFingermarks play an important role in document identification. At the same time, fingermarks on paper documents are often accompanied by signatures and background text, which introduce noise to the original fingermark textures and increase the difficulty of detection. A signed fingermark detection method based on deep residual networks and a decision-level fusion strategy was proposed to defend against spoofing attacks from fake fingermarks. Firstly, the multi-scale structure was introduced in the residual module, which improved the network’s depth and breadth without increasing the parameters. Then, the multi-probability label strategy was refined and employed to enhance the local encoding ability of the feature extraction. A score fusion strategy was designed, with weights allocated based on the difference in signed interference levels of local image blocks. Finally, a model fusion strategy based on evidence theory was suggested, which improved detection accuracy by leveraging complementarity between models. A large-scale fingermark database was established, which included real fingermarks made from real fingers and fake fingermarks made from various materials, and this was divided into two sub databases: signed and unsigned. The experimental results show that the proposed method achieves 96.16% accuracy based on the fingerprint dataset of the global liveness detection competition called LivDet2017 and achieves 99.30% accuracy based on the signed fingermark database, while it has good resistance to spoofing attacks from unknown materials.https://www.mdpi.com/2076-3417/14/5/1998biometric recognitionsigned fingermarkliveness detectiondeep residual networkdecision-level fusion |
spellingShingle | Yongliang Zhang Zihan Zhou Jiahang Wang Zipeng Chen Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision Fusion Applied Sciences biometric recognition signed fingermark liveness detection deep residual network decision-level fusion |
title | Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision Fusion |
title_full | Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision Fusion |
title_fullStr | Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision Fusion |
title_full_unstemmed | Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision Fusion |
title_short | Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision Fusion |
title_sort | signed fingermark liveness detection method based on deep residual networks and multimodal decision fusion |
topic | biometric recognition signed fingermark liveness detection deep residual network decision-level fusion |
url | https://www.mdpi.com/2076-3417/14/5/1998 |
work_keys_str_mv | AT yongliangzhang signedfingermarklivenessdetectionmethodbasedondeepresidualnetworksandmultimodaldecisionfusion AT zihanzhou signedfingermarklivenessdetectionmethodbasedondeepresidualnetworksandmultimodaldecisionfusion AT jiahangwang signedfingermarklivenessdetectionmethodbasedondeepresidualnetworksandmultimodaldecisionfusion AT zipengchen signedfingermarklivenessdetectionmethodbasedondeepresidualnetworksandmultimodaldecisionfusion |