0436547 20240103205225.120150119235959.9 84928523007 000380564200009 10.1109/SITIS.2014.48 8 s. P cav_un_epca*0436546978-1-4799-7978-349-56Los Alamitos, USAIEEE Computer Society CPS2014YetongnoKokouDipandaAlbertChbeirRichard iris occlusions detection textural model cav_un_auth*0101093 Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition Haindl Michal UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0292156 Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition Krupička Mikuláš UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2014/RO/haindl-0436547.pdf cav_un_auth*0303439 GA14-10911S GA ČR CZ Accurate detection of iris eyelids and reflections is the prerequisite for the accurate iris recognition, both in near-infrared or visible spectrum measurements. Undected iris occlusions otherwise dramatically decrease the iris recognition rate. This paper presents a fast multispectral iris occlusions detection method based on the underlying multispectral spatial probabilistic iris textural model and adaptive thresholding. The model adaptively learns its parameters on the iris texture part and subsequently checks for iris reflections, eyelashes, and eyelids using the recursive prediction analysis. Our method obtains better accuracy with respect to the previously performed Noisy Iris Challenge Evaluation contest. It ranked first from the 97+2 alternative methods on this large colour iris database. cav_un_auth*0310868 Tenth International Conference on Signal-Image Technology & Internet-Based Systems (SITIS 2014) 23.11.2014-27.11.2014 Marrakech MA BD 2015 2 PR RVO:67985556 http://hdl.handle.net/11104/0242825 S 2014 84928523007 SCOPUS 000380564200009 WOS cav_un_epca*0436546 Proceedings of the Tenth International Conference on Signal-Image Technology & Internet-Based Systems, SITIS 2014 978-1-4799-7978-3 49 56 Los Alamitos, USA IEEE Computer Society CPS 2014 Yetongno Kokou 340 Dipanda Albert 340 Chbeir Richard 340