Project Sponsor
Bundesamt für Sicherheit in der Informationstechnik (BSI)
Project Partners
National Institute of Standards and Technology (NIST)
Fraunhofer IGD (IGD)
secunet Security Networks AG (SEC)
Hochschule Darmstadt (da/sec)
NTNU (NBL)
Contact
Christoph Busch
Email: christoph.buschh-da.de
Martin Olsen
NFIQ 2
Fingerprint Image Quality
Biometric system accuracy is highly dependent on the sample quality achieved during the capture process. In fingerprint recognition the sample quality is influenced by factors such as sensor interface design and standards compliance. Improving these factors can lead to improved quality which in turn leads to better biometric performance. Aspects of the character of the fingerprint (scars, skin humidity, etc.) are not easily controlled therefore the ability to assess and reject low-quality samples becomes crucial to maintain a high performance. The outcome of the project is an open-source framework and reference implementation of fingerprint quality assessment algorithms which can be deployed in commercial and government applications. The project will improve and extend the successful NFIQ (NIST Fingerprint Image Quality) project
Further Information
- ISO/IEC 29794-1:2024 Biometric sample quality - Part 1: Framework standard
- ISO/IEC 29794-4:2024 Biometric sample quality - Part 4: Finger image data standard
- NIST NFIQ 2 Homepage
- NIST IR 8382 NFIQ 2 report
- The NFIQ 2.3 in GitHub link
- The NFIQ 2.3 FAQ
- The matlab implementation
- NFIQ2.0 features: Publication in IET Biometrics 2016
- NFIQ2.0 Light: Publication at CVPR 2013
- NIST IR 7973 Towards NFIQ2.0 Light