Abstract
The conventional finger-vein recognition system is trained using one type of database and entails the serious problem of performance degradation when tested with different types of databases. This degradation is caused by changes in image characteristics due to variable factors such as position of camera, finger, and lighting. Therefore, each database has varying characteristics despite the same finger-vein modality. However, previous researches on improving the recognition accuracy of unobserved or heterogeneous databases is lacking. To overcome this problem, we propose a method to improve the finger-vein recognition accuracy using domain adaptation between heterogeneous databases using cycle-consistent adversarial networks (CycleGAN), which enhances the recognition accuracy of unobserved data. The experiments were performed with two open databases—Shandong University homologous multi-modal traits finger-vein database (SDUMLA-HMT-DB) and Hong Kong Polytech University finger-image database (HKPolyU-DB). They showed that the equal error rate (EER) of finger-vein recognition was 0.85% in case of training with SDUMLA-HMT-DB and testing with HKPolyU-DB, which had an improvement of 33.1% compared to the second best method. The EER was 3.4% in case of training with HKPolyU-DB and testing with SDUMLA-HMT-DB, which also had an improvement of 4.8% compared to the second best method.
Highlights
Finger-vein images are difficult to forge and easy to obtain, but the image qualities are affected by the shades inevitably generated by other biological tissues [1,2]
For mitigating the trade-off between recognition performance and generality, this study proposes a method for improving the finger-vein recognition rate of cross-domain databases through finger-vein domain adaptation using cycle-consistent adversarial networks (CycleGAN)
HKPolyU-DB session 1 consists of 1872 images; two fingers of 156 persons were used for image acquisition, and six images were captured for each finger
Summary
Finger-vein images are difficult to forge and easy to obtain, but the image qualities are affected by the shades inevitably generated by other biological tissues (e.g., bone and fingernail) [1,2]. Models trained using such a dataset are ineffective for unobserved data To consider this issue, non-training-based finger-vein recognition methods have been studied extensively to overcome this drawback. Non-training-based finger-vein recognition methods have been studied extensively to overcome this drawback They exhibit significantly poorer performance than training-based methods because a large amount of information is removed by noise, making the classifier incapable of making an accurate decision [1,2,3]. Variations in the environment when acquiring images such as the camera position, lighting position, and lighting intensity create a large discrepancy between each dataset domain. This deteriorates the performance of non-training-based methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
