An enhanced segmentation approach for iris detection

Husam A El Lahrash, Md. Jan Nordin

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

With the increase of advanced development in security technology, many major corporations and governments start employing modern techniques to identify the identity of the individuals. Biometric identification methods, including facial recognition, fingerprint recognition, speech verification, and iris recognition present a new solution for applications that require a high degree of security. Among these biometric methods, iris recognition becomes an important topic in biometric recognition because it depends on iris which is located in a place that still stable through human life and the probability to find identical iris's is close to zero. The identification system consists of several stages including segmentation stage which is the most serious and critical one. The current segmentation methods still have limitation in localizing the iris due to circular shape consideration of the pupil. In this research a study for two segmentation methods of iris, Daugman method Jin method is done to investigate the segmentation techniques. Furthermore, an enhanced method based on the techniques of the mentioned two methods is proposed, which can guarantee the accuracy of the iris identification system. The proposed method takes into account the elliptical shape of the pupil and iris. Eyelid detection is another step that has been included in this study as a part of segmentation stage to localize the iris accurately and remove unwanted area that might be included. The dataset which is used for the study is CASIA v3 including the three subsets: Interval, Lamp and Twin. The evaluation way of the proposed method is done by determining the number of success images and gains a result of 98.5% which is a good result among existing methods.

Original languageEnglish
Pages (from-to)179-190
Number of pages12
JournalEuropean Journal of Scientific Research
Volume59
Issue number2
Publication statusPublished - 2011

Fingerprint

iris (eyes)
Iris
Biometrics
segmentation
Segmentation
Identification (control systems)
biometry
Speech recognition
Electric lamps
methodology
Iris Recognition
Pupil
System Identification
Biometric Identification
detection
method
Industry
Fingerprint Recognition
identification method
students

Keywords

  • Eyelid detection
  • Iris detection
  • Iris segmentation
  • Pupil localization

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Earth and Planetary Sciences(all)
  • Engineering(all)
  • Materials Science(all)
  • Mathematics(all)
  • Computer Science(all)

Cite this

An enhanced segmentation approach for iris detection. / Lahrash, Husam A El; Nordin, Md. Jan.

In: European Journal of Scientific Research, Vol. 59, No. 2, 2011, p. 179-190.

Research output: Contribution to journalArticle

@article{294ec138d8ab415ba9096357235ccbe8,
title = "An enhanced segmentation approach for iris detection",
abstract = "With the increase of advanced development in security technology, many major corporations and governments start employing modern techniques to identify the identity of the individuals. Biometric identification methods, including facial recognition, fingerprint recognition, speech verification, and iris recognition present a new solution for applications that require a high degree of security. Among these biometric methods, iris recognition becomes an important topic in biometric recognition because it depends on iris which is located in a place that still stable through human life and the probability to find identical iris's is close to zero. The identification system consists of several stages including segmentation stage which is the most serious and critical one. The current segmentation methods still have limitation in localizing the iris due to circular shape consideration of the pupil. In this research a study for two segmentation methods of iris, Daugman method Jin method is done to investigate the segmentation techniques. Furthermore, an enhanced method based on the techniques of the mentioned two methods is proposed, which can guarantee the accuracy of the iris identification system. The proposed method takes into account the elliptical shape of the pupil and iris. Eyelid detection is another step that has been included in this study as a part of segmentation stage to localize the iris accurately and remove unwanted area that might be included. The dataset which is used for the study is CASIA v3 including the three subsets: Interval, Lamp and Twin. The evaluation way of the proposed method is done by determining the number of success images and gains a result of 98.5{\%} which is a good result among existing methods.",
keywords = "Eyelid detection, Iris detection, Iris segmentation, Pupil localization",
author = "Lahrash, {Husam A El} and Nordin, {Md. Jan}",
year = "2011",
language = "English",
volume = "59",
pages = "179--190",
journal = "European Journal of Scientific Research",
issn = "1450-202X",
publisher = "European Journals Inc.",
number = "2",

}

TY - JOUR

T1 - An enhanced segmentation approach for iris detection

AU - Lahrash, Husam A El

AU - Nordin, Md. Jan

PY - 2011

Y1 - 2011

N2 - With the increase of advanced development in security technology, many major corporations and governments start employing modern techniques to identify the identity of the individuals. Biometric identification methods, including facial recognition, fingerprint recognition, speech verification, and iris recognition present a new solution for applications that require a high degree of security. Among these biometric methods, iris recognition becomes an important topic in biometric recognition because it depends on iris which is located in a place that still stable through human life and the probability to find identical iris's is close to zero. The identification system consists of several stages including segmentation stage which is the most serious and critical one. The current segmentation methods still have limitation in localizing the iris due to circular shape consideration of the pupil. In this research a study for two segmentation methods of iris, Daugman method Jin method is done to investigate the segmentation techniques. Furthermore, an enhanced method based on the techniques of the mentioned two methods is proposed, which can guarantee the accuracy of the iris identification system. The proposed method takes into account the elliptical shape of the pupil and iris. Eyelid detection is another step that has been included in this study as a part of segmentation stage to localize the iris accurately and remove unwanted area that might be included. The dataset which is used for the study is CASIA v3 including the three subsets: Interval, Lamp and Twin. The evaluation way of the proposed method is done by determining the number of success images and gains a result of 98.5% which is a good result among existing methods.

AB - With the increase of advanced development in security technology, many major corporations and governments start employing modern techniques to identify the identity of the individuals. Biometric identification methods, including facial recognition, fingerprint recognition, speech verification, and iris recognition present a new solution for applications that require a high degree of security. Among these biometric methods, iris recognition becomes an important topic in biometric recognition because it depends on iris which is located in a place that still stable through human life and the probability to find identical iris's is close to zero. The identification system consists of several stages including segmentation stage which is the most serious and critical one. The current segmentation methods still have limitation in localizing the iris due to circular shape consideration of the pupil. In this research a study for two segmentation methods of iris, Daugman method Jin method is done to investigate the segmentation techniques. Furthermore, an enhanced method based on the techniques of the mentioned two methods is proposed, which can guarantee the accuracy of the iris identification system. The proposed method takes into account the elliptical shape of the pupil and iris. Eyelid detection is another step that has been included in this study as a part of segmentation stage to localize the iris accurately and remove unwanted area that might be included. The dataset which is used for the study is CASIA v3 including the three subsets: Interval, Lamp and Twin. The evaluation way of the proposed method is done by determining the number of success images and gains a result of 98.5% which is a good result among existing methods.

KW - Eyelid detection

KW - Iris detection

KW - Iris segmentation

KW - Pupil localization

UR - http://www.scopus.com/inward/record.url?scp=80052980672&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052980672&partnerID=8YFLogxK

M3 - Article

VL - 59

SP - 179

EP - 190

JO - European Journal of Scientific Research

JF - European Journal of Scientific Research

SN - 1450-202X

IS - 2

ER -