Iris segmentation and normalization approach

Iris is a desirable biometric representation of an individual for security-related applications. However the iris segmentation and normalization process is challenging due to the presence of eye lashes that occlude the iris, the dilation of pupils due to different light illumination and several othe...

Full description

Bibliographic Details
Main Authors: Shamsi, Mahboubeh, Saad, Puteh, Rasouli, Abdolreza
Format: Article
Language:English
Published: Penerbit UTM Press 2008
Subjects:
Online Access:http://eprints.utm.my/11006/1/MahboubehShamsi2008_IrisSegmentationandNormalizationApproach.pdf
_version_ 1825910592519536640
author Shamsi, Mahboubeh
Saad, Puteh
Rasouli, Abdolreza
author_facet Shamsi, Mahboubeh
Saad, Puteh
Rasouli, Abdolreza
author_sort Shamsi, Mahboubeh
collection ePrints
description Iris is a desirable biometric representation of an individual for security-related applications. However the iris segmentation and normalization process is challenging due to the presence of eye lashes that occlude the iris, the dilation of pupils due to different light illumination and several other uncontrolled factors. In this work, we enhanced Daugman method to locate the iris and normalized it from polar to Cartesian coordinate. Iris is located by using a variable parameter binning approach. The algorithm is tested using iris images from CASIA database and MMU database. The percentage detection on MMU iris database is 99% and that of CASIA is 98%. Our approach is feasible to produce an iris template for identity identification and biometric watermarking application.
first_indexed 2024-03-05T18:19:23Z
format Article
id utm.eprints-11006
institution Universiti Teknologi Malaysia - ePrints
language English
last_indexed 2024-03-05T18:19:23Z
publishDate 2008
publisher Penerbit UTM Press
record_format dspace
spelling utm.eprints-110062017-11-01T04:17:23Z http://eprints.utm.my/11006/ Iris segmentation and normalization approach Shamsi, Mahboubeh Saad, Puteh Rasouli, Abdolreza QA75 Electronic computers. Computer science Iris is a desirable biometric representation of an individual for security-related applications. However the iris segmentation and normalization process is challenging due to the presence of eye lashes that occlude the iris, the dilation of pupils due to different light illumination and several other uncontrolled factors. In this work, we enhanced Daugman method to locate the iris and normalized it from polar to Cartesian coordinate. Iris is located by using a variable parameter binning approach. The algorithm is tested using iris images from CASIA database and MMU database. The percentage detection on MMU iris database is 99% and that of CASIA is 98%. Our approach is feasible to produce an iris template for identity identification and biometric watermarking application. Penerbit UTM Press 2008-12 Article PeerReviewed application/pdf en http://eprints.utm.my/11006/1/MahboubehShamsi2008_IrisSegmentationandNormalizationApproach.pdf Shamsi, Mahboubeh and Saad, Puteh and Rasouli, Abdolreza (2008) Iris segmentation and normalization approach. Jurnal Teknologi Maklumat, 20 (3). pp. 88-101. ISSN 0128-3790
spellingShingle QA75 Electronic computers. Computer science
Shamsi, Mahboubeh
Saad, Puteh
Rasouli, Abdolreza
Iris segmentation and normalization approach
title Iris segmentation and normalization approach
title_full Iris segmentation and normalization approach
title_fullStr Iris segmentation and normalization approach
title_full_unstemmed Iris segmentation and normalization approach
title_short Iris segmentation and normalization approach
title_sort iris segmentation and normalization approach
topic QA75 Electronic computers. Computer science
url http://eprints.utm.my/11006/1/MahboubehShamsi2008_IrisSegmentationandNormalizationApproach.pdf
work_keys_str_mv AT shamsimahboubeh irissegmentationandnormalizationapproach
AT saadputeh irissegmentationandnormalizationapproach
AT rasouliabdolreza irissegmentationandnormalizationapproach