Accurate iris segmentation method for non-cooperative iris recognition system

Abdulsamad Ebrahim Yahya, Md. Jan Nordin

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Problem statement: Iris segmentation is one of the most important steps in iris recognition system and determines the accuracy of matching. Most segmentation methods in the literature assumed that the inner and outer boundaries of the iris were circular. Hence, they focus on determining model parameters that best fit these hypotheses. This is a source of error, since the iris boundaries were not exactly circles. Approach: In this study we proposed an accurate iris segmentation method that employs Chan-Vese active contour method to extract the iris from his surrounding structures. Results: The proposed method was implemented and tested on the challenging UBIRIS database the results indicated the efficacy of the proposed method. Conclusion: The experimental results showed that the proposed method localized the iris area probably even when the eyelids occlude same part of iris.

Original languageEnglish
Pages (from-to)492-497
Number of pages6
JournalJournal of Computer Science
Volume6
Issue number5
DOIs
Publication statusPublished - 2010

Keywords

  • Adaboost detection
  • Chan-Vese active contours
  • Iris segmentation

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Accurate iris segmentation method for non-cooperative iris recognition system. / Yahya, Abdulsamad Ebrahim; Nordin, Md. Jan.

In: Journal of Computer Science, Vol. 6, No. 5, 2010, p. 492-497.

Research output: Contribution to journalArticle

@article{6143014c198947ecb611d5ff2cf2f5b9,
title = "Accurate iris segmentation method for non-cooperative iris recognition system",
abstract = "Problem statement: Iris segmentation is one of the most important steps in iris recognition system and determines the accuracy of matching. Most segmentation methods in the literature assumed that the inner and outer boundaries of the iris were circular. Hence, they focus on determining model parameters that best fit these hypotheses. This is a source of error, since the iris boundaries were not exactly circles. Approach: In this study we proposed an accurate iris segmentation method that employs Chan-Vese active contour method to extract the iris from his surrounding structures. Results: The proposed method was implemented and tested on the challenging UBIRIS database the results indicated the efficacy of the proposed method. Conclusion: The experimental results showed that the proposed method localized the iris area probably even when the eyelids occlude same part of iris.",
keywords = "Adaboost detection, Chan-Vese active contours, Iris segmentation",
author = "Yahya, {Abdulsamad Ebrahim} and Nordin, {Md. Jan}",
year = "2010",
doi = "10.3844/jcssp.2010.492.497",
language = "English",
volume = "6",
pages = "492--497",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "5",

}

TY - JOUR

T1 - Accurate iris segmentation method for non-cooperative iris recognition system

AU - Yahya, Abdulsamad Ebrahim

AU - Nordin, Md. Jan

PY - 2010

Y1 - 2010

N2 - Problem statement: Iris segmentation is one of the most important steps in iris recognition system and determines the accuracy of matching. Most segmentation methods in the literature assumed that the inner and outer boundaries of the iris were circular. Hence, they focus on determining model parameters that best fit these hypotheses. This is a source of error, since the iris boundaries were not exactly circles. Approach: In this study we proposed an accurate iris segmentation method that employs Chan-Vese active contour method to extract the iris from his surrounding structures. Results: The proposed method was implemented and tested on the challenging UBIRIS database the results indicated the efficacy of the proposed method. Conclusion: The experimental results showed that the proposed method localized the iris area probably even when the eyelids occlude same part of iris.

AB - Problem statement: Iris segmentation is one of the most important steps in iris recognition system and determines the accuracy of matching. Most segmentation methods in the literature assumed that the inner and outer boundaries of the iris were circular. Hence, they focus on determining model parameters that best fit these hypotheses. This is a source of error, since the iris boundaries were not exactly circles. Approach: In this study we proposed an accurate iris segmentation method that employs Chan-Vese active contour method to extract the iris from his surrounding structures. Results: The proposed method was implemented and tested on the challenging UBIRIS database the results indicated the efficacy of the proposed method. Conclusion: The experimental results showed that the proposed method localized the iris area probably even when the eyelids occlude same part of iris.

KW - Adaboost detection

KW - Chan-Vese active contours

KW - Iris segmentation

UR - http://www.scopus.com/inward/record.url?scp=78049525746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049525746&partnerID=8YFLogxK

U2 - 10.3844/jcssp.2010.492.497

DO - 10.3844/jcssp.2010.492.497

M3 - Article

AN - SCOPUS:78049525746

VL - 6

SP - 492

EP - 497

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 5

ER -