Non-Iris Occlusions Detection

0397243 - ÚTIA 2014 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Haindl, Michal - Krupička, Mikuláš
Non-Iris Occlusions Detection.
Biometrics: Theory, Applications and Systems (BTAS), 2013. Piscataway: IEEE, 2013, s. 1-6. ISBN 978-1-4799-0527-0.
[The IEEE Sixth International Conference on Biometrics: Theory, Applications, and Systems (BTAS 2013). Washington DC (US), 29.09.2013-02.10.2013]
Grant CEP: GA ČR GAP103/11/0335; GA ČR GA102/08/0593
Institucionální podpora: RVO:67985556
Klíčová slova: iris recognition * iris occlusion
Kód oboru RIV: BD - Teorie informace
http://library.utia.cas.cz/separaty/2013/RO/haindl-0397243.pdf

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.
Trvalý link: http://hdl.handle.net/11104/0225895