Number of the records: 1
Non-Iris Occlusions Detection
- 1.
SYSNO ASEP 0397243 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Non-Iris Occlusions Detection Author(s) Haindl, Michal (UTIA-B) RID, ORCID
Krupička, Mikuláš (UTIA-B) RIDNumber of authors 2 Source Title Biometrics: Theory, Applications and Systems (BTAS), 2013. - Piscataway : IEEE, 2013 - ISBN 978-1-4799-0527-0 Pages s. 1-6 Number of pages 6 s. Publication form Medium - C Action The IEEE Sixth International Conference on Biometrics: Theory, Applications, and Systems (BTAS 2013) Event date 29.09.2013-02.10.2013 VEvent location Washington DC Country US - United States Event type WRD Language eng - English Country US - United States Keywords iris recognition ; iris occlusion Subject RIV BD - Theory of Information R&D Projects GAP103/11/0335 GA ČR - Czech Science Foundation (CSF) GA102/08/0593 GA ČR - Czech Science Foundation (CSF) Institutional support UTIA-B - RVO:67985556 UT WOS 000336080600044 DOI 10.1109/BTAS.2013.6712729 Annotation The prerequisite for the accurate iris recognition is to detect all iris occlusions which would otherwise confuse a recognition method and impair its recognition rate. This paper presents a fast multispectral eyelid, eyelash, and reflection detection method based on the underlying three-dimensional spatial probabilistic textural model. The model first adaptively learns its parameters on the flawless iris texture part and subsequently checks for non iris occlusions using the recursive prediction analysis. We provide colour iris occlusion detection results that indicate the advantages of the proposed method and compare it with 97 recent Noisy Iris Challenge Evaluation algorithms. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2014
Number of the records: 1