Feature extraction for iris recognition

Jinwook Go, Gyundo Kee, Jain Jang, Yillbyung Lee, Chulhee Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we evaluate performances of various feature extraction methods for iris pattern classification. Generally, an identification system using iris recognition consists of 4 stages: image acquisition, preprocessing, feature extraction and pattern matching. In this paper, we used the 2D bisection-based Hough transform and the radius histogram method for localizing the iris and used multilayer neural networks as a classifier. In order to further reduce the number of features, three linear feature extraction methods are evaluated. In particular, by using an efficient feature extraction algorithm, we explore the possibility to reduce the classification time and system complexity for a large iris data set. The tested feature extraction methods are the feature extraction based on decision boundary, canonical analysis, and principal component analysis. Experiments with 1831 iris images show that the feature extraction based on decision boundary and canonical analysis provide a favorable performance.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Artificial Intelligence IC-AI 2003
EditorsH.R. Arabnia, R. Joshua, Y. Mun, H.R. Arabnia, R. Joshua, Y. Mun
Pages304-309
Number of pages6
Publication statusPublished - 2003 Dec 1
EventProceedings of the International Conference on Artificial Intelligence, IC-AI 2003 - Las Vegas, NV, United States
Duration: 2003 Jun 232003 Jun 26

Publication series

NameProceedings of the International Conference on Artificial Intelligence IC-AI 2003
Volume1

Other

OtherProceedings of the International Conference on Artificial Intelligence, IC-AI 2003
CountryUnited States
CityLas Vegas, NV
Period03/6/2303/6/26

Fingerprint

Feature extraction
Hough transforms
Pattern matching
Image acquisition
Multilayer neural networks
Principal component analysis
Pattern recognition
Identification (control systems)
Classifiers
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Go, J., Kee, G., Jang, J., Lee, Y., & Lee, C. (2003). Feature extraction for iris recognition. In H. R. Arabnia, R. Joshua, Y. Mun, H. R. Arabnia, R. Joshua, & Y. Mun (Eds.), Proceedings of the International Conference on Artificial Intelligence IC-AI 2003 (pp. 304-309). (Proceedings of the International Conference on Artificial Intelligence IC-AI 2003; Vol. 1).
Go, Jinwook ; Kee, Gyundo ; Jang, Jain ; Lee, Yillbyung ; Lee, Chulhee. / Feature extraction for iris recognition. Proceedings of the International Conference on Artificial Intelligence IC-AI 2003. editor / H.R. Arabnia ; R. Joshua ; Y. Mun ; H.R. Arabnia ; R. Joshua ; Y. Mun. 2003. pp. 304-309 (Proceedings of the International Conference on Artificial Intelligence IC-AI 2003).
@inproceedings{7e178b6e0fe244289feff016dd0b9329,
title = "Feature extraction for iris recognition",
abstract = "In this paper, we evaluate performances of various feature extraction methods for iris pattern classification. Generally, an identification system using iris recognition consists of 4 stages: image acquisition, preprocessing, feature extraction and pattern matching. In this paper, we used the 2D bisection-based Hough transform and the radius histogram method for localizing the iris and used multilayer neural networks as a classifier. In order to further reduce the number of features, three linear feature extraction methods are evaluated. In particular, by using an efficient feature extraction algorithm, we explore the possibility to reduce the classification time and system complexity for a large iris data set. The tested feature extraction methods are the feature extraction based on decision boundary, canonical analysis, and principal component analysis. Experiments with 1831 iris images show that the feature extraction based on decision boundary and canonical analysis provide a favorable performance.",
author = "Jinwook Go and Gyundo Kee and Jain Jang and Yillbyung Lee and Chulhee Lee",
year = "2003",
month = "12",
day = "1",
language = "English",
isbn = "1932415122",
series = "Proceedings of the International Conference on Artificial Intelligence IC-AI 2003",
pages = "304--309",
editor = "H.R. Arabnia and R. Joshua and Y. Mun and H.R. Arabnia and R. Joshua and Y. Mun",
booktitle = "Proceedings of the International Conference on Artificial Intelligence IC-AI 2003",

}

Go, J, Kee, G, Jang, J, Lee, Y & Lee, C 2003, Feature extraction for iris recognition. in HR Arabnia, R Joshua, Y Mun, HR Arabnia, R Joshua & Y Mun (eds), Proceedings of the International Conference on Artificial Intelligence IC-AI 2003. Proceedings of the International Conference on Artificial Intelligence IC-AI 2003, vol. 1, pp. 304-309, Proceedings of the International Conference on Artificial Intelligence, IC-AI 2003, Las Vegas, NV, United States, 03/6/23.

Feature extraction for iris recognition. / Go, Jinwook; Kee, Gyundo; Jang, Jain; Lee, Yillbyung; Lee, Chulhee.

Proceedings of the International Conference on Artificial Intelligence IC-AI 2003. ed. / H.R. Arabnia; R. Joshua; Y. Mun; H.R. Arabnia; R. Joshua; Y. Mun. 2003. p. 304-309 (Proceedings of the International Conference on Artificial Intelligence IC-AI 2003; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Feature extraction for iris recognition

AU - Go, Jinwook

AU - Kee, Gyundo

AU - Jang, Jain

AU - Lee, Yillbyung

AU - Lee, Chulhee

PY - 2003/12/1

Y1 - 2003/12/1

N2 - In this paper, we evaluate performances of various feature extraction methods for iris pattern classification. Generally, an identification system using iris recognition consists of 4 stages: image acquisition, preprocessing, feature extraction and pattern matching. In this paper, we used the 2D bisection-based Hough transform and the radius histogram method for localizing the iris and used multilayer neural networks as a classifier. In order to further reduce the number of features, three linear feature extraction methods are evaluated. In particular, by using an efficient feature extraction algorithm, we explore the possibility to reduce the classification time and system complexity for a large iris data set. The tested feature extraction methods are the feature extraction based on decision boundary, canonical analysis, and principal component analysis. Experiments with 1831 iris images show that the feature extraction based on decision boundary and canonical analysis provide a favorable performance.

AB - In this paper, we evaluate performances of various feature extraction methods for iris pattern classification. Generally, an identification system using iris recognition consists of 4 stages: image acquisition, preprocessing, feature extraction and pattern matching. In this paper, we used the 2D bisection-based Hough transform and the radius histogram method for localizing the iris and used multilayer neural networks as a classifier. In order to further reduce the number of features, three linear feature extraction methods are evaluated. In particular, by using an efficient feature extraction algorithm, we explore the possibility to reduce the classification time and system complexity for a large iris data set. The tested feature extraction methods are the feature extraction based on decision boundary, canonical analysis, and principal component analysis. Experiments with 1831 iris images show that the feature extraction based on decision boundary and canonical analysis provide a favorable performance.

UR - http://www.scopus.com/inward/record.url?scp=1642266371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1642266371&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:1642266371

SN - 1932415122

T3 - Proceedings of the International Conference on Artificial Intelligence IC-AI 2003

SP - 304

EP - 309

BT - Proceedings of the International Conference on Artificial Intelligence IC-AI 2003

A2 - Arabnia, H.R.

A2 - Joshua, R.

A2 - Mun, Y.

A2 - Arabnia, H.R.

A2 - Joshua, R.

A2 - Mun, Y.

ER -

Go J, Kee G, Jang J, Lee Y, Lee C. Feature extraction for iris recognition. In Arabnia HR, Joshua R, Mun Y, Arabnia HR, Joshua R, Mun Y, editors, Proceedings of the International Conference on Artificial Intelligence IC-AI 2003. 2003. p. 304-309. (Proceedings of the International Conference on Artificial Intelligence IC-AI 2003).