Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Towards touchless palm and finger detection for fingerprint extraction with mobile devices

 
: Jonietz, Christof; Monari, Eduardo; Qu, Chengchao

:
Preprint urn:nbn:de:0011-n-3643201 (1.2 MByte PDF)
MD5 Fingerprint: 699aab264c95632d17ef8b9a75d4830d
Erstellt am: 18.11.2015


Brömme, Arslan (Hrsg.) ; Gesellschaft für Informatik -GI-, Fachgruppe Biometrik und Elektronische Signaturen:
BIOSIG 2015 : Proceedings of the 14th International Conference of the Biometrics Special Interest Group, 09.-11. September 2015 in Darmstadt, Germany
Bonn: Köllen, 2015 (GI-Edition - Lecture Notes in Informatics (LNI) - Proceedings 245)
ISBN: 3-88579-639-2
ISBN: 978-3-88579-639-8
8 S.
Gesellschaft für Informatik, Special Interest Group on Biometrics and Electronic Signatures (BIOSIG International Conference) <14, 2015, Darmstadt>
European Commission EC
FP7-SECURITY; 608016; MOBILEPASS
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()

Abstract
In this paper, contactless palm and finger detection for biometric fingerprint
verification/identification process with mobile devices is considered. In order to speed up the border checking verification process, we focus on capturing the whole palm in order to extract each fingertip instead of successively capturing each fingertip. The workflow comprises palm detection in order to detect the skin region within the image prior to detection of fingertips. A machine learning based algorithm with Aggregated Channel Features (ACFs) adopted for palm detection is considered. Furthermore, a geometric shape based approach for fingertip detection has been designed to reconstruct long lines along fingers. Results demonstrate the performance of both algorithms.

: http://publica.fraunhofer.de/dokumente/N-364320.html