Iris Segmentation in Visible Wavelength Images using Circular Gabor Filters and Optimization

Abduljalil Radman, Kasmiran Jumari, Nasharuddin Zainal

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Segmenting iris from images captured under the visible wavelength spectrum represents a challenging task. To address this problem, a new iris segmentation method based on the Circular Gabor Filter (CGF) and optimization is proposed. The CGF is utilized to localize the rough position of the pupil center. According to the localization result, few pixels of the pupil (iris) and non-pupil (non-iris) regions are set as initial pixels in the related region. Next, by optimization scheme, initial pixels are automatically propagated over the image until they cover the whole pupil (iris) and non-pupil (non-iris) regions. The originality of the proposed method includes developing a new method to localize the iris and eyelids boundaries simultaneously, and furthermore robust to reflections. Experimental results on the non-cooperative UBIRIS.v1 iris images reveal the effectiveness of the proposed method in comparison with some of state-of-the-art methods. The results include classification error rates of 2.08 and 3.05 % for session one and two of the UBIRIS.v1 database, respectively.

Original languageEnglish
Pages (from-to)3039-3049
Number of pages11
JournalArabian Journal for Science and Engineering
Volume39
Issue number4
DOIs
Publication statusPublished - 2014

Fingerprint

Gabor filters
Pixels
Wavelength

Keywords

  • Circular Gabor filter
  • Iris segmentation
  • Non-cooperative iris recognition
  • Optimization

ASJC Scopus subject areas

  • General

Cite this

Iris Segmentation in Visible Wavelength Images using Circular Gabor Filters and Optimization. / Radman, Abduljalil; Jumari, Kasmiran; Zainal, Nasharuddin.

In: Arabian Journal for Science and Engineering, Vol. 39, No. 4, 2014, p. 3039-3049.

Research output: Contribution to journalArticle

@article{eee532753a784428a45e438f14437ada,
title = "Iris Segmentation in Visible Wavelength Images using Circular Gabor Filters and Optimization",
abstract = "Segmenting iris from images captured under the visible wavelength spectrum represents a challenging task. To address this problem, a new iris segmentation method based on the Circular Gabor Filter (CGF) and optimization is proposed. The CGF is utilized to localize the rough position of the pupil center. According to the localization result, few pixels of the pupil (iris) and non-pupil (non-iris) regions are set as initial pixels in the related region. Next, by optimization scheme, initial pixels are automatically propagated over the image until they cover the whole pupil (iris) and non-pupil (non-iris) regions. The originality of the proposed method includes developing a new method to localize the iris and eyelids boundaries simultaneously, and furthermore robust to reflections. Experimental results on the non-cooperative UBIRIS.v1 iris images reveal the effectiveness of the proposed method in comparison with some of state-of-the-art methods. The results include classification error rates of 2.08 and 3.05 {\%} for session one and two of the UBIRIS.v1 database, respectively.",
keywords = "Circular Gabor filter, Iris segmentation, Non-cooperative iris recognition, Optimization",
author = "Abduljalil Radman and Kasmiran Jumari and Nasharuddin Zainal",
year = "2014",
doi = "10.1007/s13369-013-0924-3",
language = "English",
volume = "39",
pages = "3039--3049",
journal = "Arabian Journal for Science and Engineering",
issn = "1319-8025",
publisher = "King Fahd University of Petroleum and Minerals",
number = "4",

}

TY - JOUR

T1 - Iris Segmentation in Visible Wavelength Images using Circular Gabor Filters and Optimization

AU - Radman, Abduljalil

AU - Jumari, Kasmiran

AU - Zainal, Nasharuddin

PY - 2014

Y1 - 2014

N2 - Segmenting iris from images captured under the visible wavelength spectrum represents a challenging task. To address this problem, a new iris segmentation method based on the Circular Gabor Filter (CGF) and optimization is proposed. The CGF is utilized to localize the rough position of the pupil center. According to the localization result, few pixels of the pupil (iris) and non-pupil (non-iris) regions are set as initial pixels in the related region. Next, by optimization scheme, initial pixels are automatically propagated over the image until they cover the whole pupil (iris) and non-pupil (non-iris) regions. The originality of the proposed method includes developing a new method to localize the iris and eyelids boundaries simultaneously, and furthermore robust to reflections. Experimental results on the non-cooperative UBIRIS.v1 iris images reveal the effectiveness of the proposed method in comparison with some of state-of-the-art methods. The results include classification error rates of 2.08 and 3.05 % for session one and two of the UBIRIS.v1 database, respectively.

AB - Segmenting iris from images captured under the visible wavelength spectrum represents a challenging task. To address this problem, a new iris segmentation method based on the Circular Gabor Filter (CGF) and optimization is proposed. The CGF is utilized to localize the rough position of the pupil center. According to the localization result, few pixels of the pupil (iris) and non-pupil (non-iris) regions are set as initial pixels in the related region. Next, by optimization scheme, initial pixels are automatically propagated over the image until they cover the whole pupil (iris) and non-pupil (non-iris) regions. The originality of the proposed method includes developing a new method to localize the iris and eyelids boundaries simultaneously, and furthermore robust to reflections. Experimental results on the non-cooperative UBIRIS.v1 iris images reveal the effectiveness of the proposed method in comparison with some of state-of-the-art methods. The results include classification error rates of 2.08 and 3.05 % for session one and two of the UBIRIS.v1 database, respectively.

KW - Circular Gabor filter

KW - Iris segmentation

KW - Non-cooperative iris recognition

KW - Optimization

UR - http://www.scopus.com/inward/record.url?scp=84900036400&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900036400&partnerID=8YFLogxK

U2 - 10.1007/s13369-013-0924-3

DO - 10.1007/s13369-013-0924-3

M3 - Article

AN - SCOPUS:84900036400

VL - 39

SP - 3039

EP - 3049

JO - Arabian Journal for Science and Engineering

JF - Arabian Journal for Science and Engineering

SN - 1319-8025

IS - 4

ER -