Cargando…

Cross-spectral iris recognition using phase-based matching and homomorphic filtering

In cross-spectral iris recognition, different spectral bands are used to obtain rich information of the human iris. Previous studies on cross-spectral iris recognition are based primarily on feature-based approaches, which are prone to the changes in parameters in the feature extraction process, suc...

Descripción completa

Detalles Bibliográficos
Autores principales: Oktiana, Maulisa, Horiuchi, Takahiko, Hirai, Keita, Saddami, Khairun, Arnia, Fitri, Away, Yuwaldi, Munadi, Khairul
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7036527/
https://www.ncbi.nlm.nih.gov/pubmed/32123763
http://dx.doi.org/10.1016/j.heliyon.2020.e03407
_version_ 1783500236867502080
author Oktiana, Maulisa
Horiuchi, Takahiko
Hirai, Keita
Saddami, Khairun
Arnia, Fitri
Away, Yuwaldi
Munadi, Khairul
author_facet Oktiana, Maulisa
Horiuchi, Takahiko
Hirai, Keita
Saddami, Khairun
Arnia, Fitri
Away, Yuwaldi
Munadi, Khairul
author_sort Oktiana, Maulisa
collection PubMed
description In cross-spectral iris recognition, different spectral bands are used to obtain rich information of the human iris. Previous studies on cross-spectral iris recognition are based primarily on feature-based approaches, which are prone to the changes in parameters in the feature extraction process, such as spatial position and iris image acquisition conditions. These parameters can degrade iris recognition performance. In this paper, we present a phase-based approach for cross-spectral iris recognition using phase-only correlation (POC) and band-limited phase-only correlation (BLPOC). A phase-based iris recognition system recognizes an iris using the phase information contained in the iris image; therefore, its performance is not affected by feature extraction parameters. However, the performance of a phase-based cross-spectral iris recognition is strongly influenced by specular reflection. Different illumination conditions may produce different iris images from the same subject. To overcome this challenge, we integrate a photometric normalization technique –homomorphic filtering– with phase-based cross-spectral iris recognition. The experimental results reveal that the proposed technique achieved an excellent matching performance with an equal error rate of 0.59% and a genuine acceptance rate of 95%.
format Online
Article
Text
id pubmed-7036527
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-70365272020-03-02 Cross-spectral iris recognition using phase-based matching and homomorphic filtering Oktiana, Maulisa Horiuchi, Takahiko Hirai, Keita Saddami, Khairun Arnia, Fitri Away, Yuwaldi Munadi, Khairul Heliyon Article In cross-spectral iris recognition, different spectral bands are used to obtain rich information of the human iris. Previous studies on cross-spectral iris recognition are based primarily on feature-based approaches, which are prone to the changes in parameters in the feature extraction process, such as spatial position and iris image acquisition conditions. These parameters can degrade iris recognition performance. In this paper, we present a phase-based approach for cross-spectral iris recognition using phase-only correlation (POC) and band-limited phase-only correlation (BLPOC). A phase-based iris recognition system recognizes an iris using the phase information contained in the iris image; therefore, its performance is not affected by feature extraction parameters. However, the performance of a phase-based cross-spectral iris recognition is strongly influenced by specular reflection. Different illumination conditions may produce different iris images from the same subject. To overcome this challenge, we integrate a photometric normalization technique –homomorphic filtering– with phase-based cross-spectral iris recognition. The experimental results reveal that the proposed technique achieved an excellent matching performance with an equal error rate of 0.59% and a genuine acceptance rate of 95%. Elsevier 2020-02-20 /pmc/articles/PMC7036527/ /pubmed/32123763 http://dx.doi.org/10.1016/j.heliyon.2020.e03407 Text en © 2020 Published by Elsevier Ltd. http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Oktiana, Maulisa
Horiuchi, Takahiko
Hirai, Keita
Saddami, Khairun
Arnia, Fitri
Away, Yuwaldi
Munadi, Khairul
Cross-spectral iris recognition using phase-based matching and homomorphic filtering
title Cross-spectral iris recognition using phase-based matching and homomorphic filtering
title_full Cross-spectral iris recognition using phase-based matching and homomorphic filtering
title_fullStr Cross-spectral iris recognition using phase-based matching and homomorphic filtering
title_full_unstemmed Cross-spectral iris recognition using phase-based matching and homomorphic filtering
title_short Cross-spectral iris recognition using phase-based matching and homomorphic filtering
title_sort cross-spectral iris recognition using phase-based matching and homomorphic filtering
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7036527/
https://www.ncbi.nlm.nih.gov/pubmed/32123763
http://dx.doi.org/10.1016/j.heliyon.2020.e03407
work_keys_str_mv AT oktianamaulisa crossspectralirisrecognitionusingphasebasedmatchingandhomomorphicfiltering
AT horiuchitakahiko crossspectralirisrecognitionusingphasebasedmatchingandhomomorphicfiltering
AT hiraikeita crossspectralirisrecognitionusingphasebasedmatchingandhomomorphicfiltering
AT saddamikhairun crossspectralirisrecognitionusingphasebasedmatchingandhomomorphicfiltering
AT arniafitri crossspectralirisrecognitionusingphasebasedmatchingandhomomorphicfiltering
AT awayyuwaldi crossspectralirisrecognitionusingphasebasedmatchingandhomomorphicfiltering
AT munadikhairul crossspectralirisrecognitionusingphasebasedmatchingandhomomorphicfiltering