Abstract
The fingerprint is a commonly used biometric modality that is widely employed for authentication by law enforcement agencies and commercial applications. The designs of existing fingerprint matching methods are based on the hypothesis that the same sensor is used to capture fingerprints during enrollment and verification. Advances in fingerprint sensor technology have raised the question about the usability of current methods when different sensors are employed for enrollment and verification; this is a fingerprint sensor interoperability problem. To provide insight into this problem and assess the status of state-of-the-art matching methods to tackle this problem, we first analyze the characteristics of fingerprints captured with different sensors, which makes cross-sensor matching a challenging problem. We demonstrate the importance of fingerprint enhancement methods for cross-sensor matching. Finally, we conduct a comparative study of state-of-the-art fingerprint recognition methods and provide insight into their abilities to address this problem. We performed experiments using a public database (FingerPass) that contains nine datasets captured with different sensors. We analyzed the effects of different sensors and found that cross-sensor matching performance deteriorates when different sensors are used for enrollment and verification. In view of our analysis, we propose future research directions for this problem.
Highlights
The use of fingerprints is the oldest and most prevalent method for person identification and authentication
For evaluating the methods to assess the fingerprint sensor interoperability problem, we consider two matching scenarios: (i) Regular Matching, a comparison of two fingerprints acquired with the same sensor, in which case equal error rate (EER) is referred to as native EER, and (ii) Cross Matching, a comparison of two fingerprints captured with different sensors, in which case EER is termed as interoperable EER
We provide insight into the real issues involved in the fingerprint sensor interoperability problem
Summary
The use of fingerprints is the oldest and most prevalent method for person identification and authentication. These studies are limited in the sense that Shimon et al [2] focused only on one minutiae based matcher (VeriFinger), whereas Lugini et al [3] and Mason et al [4] employed an interoperable dataset captured with four sensors of the same technology type, which cannot be generalized to sensors of other technology types These studies were conducted on local databases; for new solutions to the problem, it is difficult to reproduce the results obtained in these evaluations and compare the performance of the new algorithms. These questions motivated us to analyze the structural inconsistencies of fingerprints captured with different sensors and provide a comparative analysis of state-of-the-art enhancement methods and matching systems to understand the effect of the fingerprint sensor interoperability problem using a public database.
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.
