DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep Reinforcement
Finger vein recognition has become a research hotspot in the field of biometrics due to its advantages of non-contact acquisition, unique information, and difficulty in terms of forging or pirating. However, in the real-world application process, the extraction of image features for the biometric re...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/2/699 |
| _version_ | 1797446751657918464 |
|---|---|
| author | Ruoran Gao Huimin Lu Adil Al-Azzawi Yupeng Li Chengcheng Zhao |
| author_facet | Ruoran Gao Huimin Lu Adil Al-Azzawi Yupeng Li Chengcheng Zhao |
| author_sort | Ruoran Gao |
| collection | DOAJ |
| description | Finger vein recognition has become a research hotspot in the field of biometrics due to its advantages of non-contact acquisition, unique information, and difficulty in terms of forging or pirating. However, in the real-world application process, the extraction of image features for the biometric remains a significant challenge when the captured finger vein images suffer from blur, noise, or missing feature information. To address the above challenges, we propose a novel deep reinforcement learning-based finger vein image recovery method, DRL-FVRestore, which trained an agent that adaptively selects the appropriate restoration behavior according to the state of the finger vein image, enabling continuous restoration of the image. The behaviors of image restoration are divided into three tasks: deblurring restoration, defect restoration, and denoising and enhancement restoration. Specifically, a DeblurGAN-v2 based on the Inception-Resnet-v2 backbone is proposed to achieve deblurring restoration of finger vein images. A finger vein feature-guided restoration network is proposed to achieve defect image restoration. The DRL-FVRestore is proposed to deal with multi-image problems in complex situations. In this paper, extensive experimental results are conducted based on using four publicly accessible datasets. The experimental results show that for restoration with single image problems, the EER values of the deblurring network and damage restoration network are reduced by an average of 4.31% and 1.71%, respectively, compared to other methods. For images with multiple vision problems, the EER value of the proposed DRL-FVRestore is reduced by an average of 3.98%. |
| first_indexed | 2024-03-09T13:46:03Z |
| format | Article |
| id | doaj.art-4bbc6fc89d95488381cde7adca8a7515 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:46:03Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4bbc6fc89d95488381cde7adca8a75152023-11-30T21:00:13ZengMDPI AGApplied Sciences2076-34172023-01-0113269910.3390/app13020699DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep ReinforcementRuoran Gao0Huimin Lu1Adil Al-Azzawi2Yupeng Li3Chengcheng Zhao4School of Computer Science and Engineering, Changchun University of Technology, Changchun 130102, ChinaSchool of Computer Science and Engineering, Changchun University of Technology, Changchun 130102, ChinaComputer Science Department, College of Art and Science, American University of Iraq-Baghdad (AUIB), Baghdad 00964, IraqSchool of Computer Science and Engineering, Changchun University of Technology, Changchun 130102, ChinaSchool of Computer Science and Engineering, Changchun University of Technology, Changchun 130102, ChinaFinger vein recognition has become a research hotspot in the field of biometrics due to its advantages of non-contact acquisition, unique information, and difficulty in terms of forging or pirating. However, in the real-world application process, the extraction of image features for the biometric remains a significant challenge when the captured finger vein images suffer from blur, noise, or missing feature information. To address the above challenges, we propose a novel deep reinforcement learning-based finger vein image recovery method, DRL-FVRestore, which trained an agent that adaptively selects the appropriate restoration behavior according to the state of the finger vein image, enabling continuous restoration of the image. The behaviors of image restoration are divided into three tasks: deblurring restoration, defect restoration, and denoising and enhancement restoration. Specifically, a DeblurGAN-v2 based on the Inception-Resnet-v2 backbone is proposed to achieve deblurring restoration of finger vein images. A finger vein feature-guided restoration network is proposed to achieve defect image restoration. The DRL-FVRestore is proposed to deal with multi-image problems in complex situations. In this paper, extensive experimental results are conducted based on using four publicly accessible datasets. The experimental results show that for restoration with single image problems, the EER values of the deblurring network and damage restoration network are reduced by an average of 4.31% and 1.71%, respectively, compared to other methods. For images with multiple vision problems, the EER value of the proposed DRL-FVRestore is reduced by an average of 3.98%.https://www.mdpi.com/2076-3417/13/2/699biometricsfinger vein recognitionimage restorationreinforcement learning |
| spellingShingle | Ruoran Gao Huimin Lu Adil Al-Azzawi Yupeng Li Chengcheng Zhao DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep Reinforcement Applied Sciences biometrics finger vein recognition image restoration reinforcement learning |
| title | DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep Reinforcement |
| title_full | DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep Reinforcement |
| title_fullStr | DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep Reinforcement |
| title_full_unstemmed | DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep Reinforcement |
| title_short | DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep Reinforcement |
| title_sort | drl fvrestore an adaptive selection and restoration method for finger vein images based on deep reinforcement |
| topic | biometrics finger vein recognition image restoration reinforcement learning |
| url | https://www.mdpi.com/2076-3417/13/2/699 |
| work_keys_str_mv | AT ruorangao drlfvrestoreanadaptiveselectionandrestorationmethodforfingerveinimagesbasedondeepreinforcement AT huiminlu drlfvrestoreanadaptiveselectionandrestorationmethodforfingerveinimagesbasedondeepreinforcement AT adilalazzawi drlfvrestoreanadaptiveselectionandrestorationmethodforfingerveinimagesbasedondeepreinforcement AT yupengli drlfvrestoreanadaptiveselectionandrestorationmethodforfingerveinimagesbasedondeepreinforcement AT chengchengzhao drlfvrestoreanadaptiveselectionandrestorationmethodforfingerveinimagesbasedondeepreinforcement |