Invariant biometric code extraction

Hyung Gu Lee, Seungin Noh, Kwanghyuk Bae, Kang Ryoung Park, Jaihie Kim

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

6 Citations (Scopus)

Abstract

We propose invariant key generation method using iris image. In conventional iris recognition system, iris features are not consistent because most feature extraction techniques are sensitive to the variations of captured iris image data. In this paper, we introduce the invariant binary feature which is defined as iris key. Regardless of iris image variations, we can extract the invariant iris key in our experiments. Our method can be applied to various fields especially for key protection and key management application using biometric data, which include e-commerce, smart card, and logging into personal computer or secured web site. To generate the iris key, we propose the reference pattern which is designed as lattice structured image to represent a bit pattern as individual's identity. The reference pattern and iris image are linked into filter. In the filter, iris texture is reflected according to magnitude of iris power spectrum in frequency domain. There is a trade-off relation-ship between with-in class tolerance and between-class discrimination, so that we can control these factors which are included in the filter. In experimental results, we were able to tune the system to a False Rejection Ratio(FRR) level of 1.0%.

Original languageEnglish
Title of host publicationProceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004
EditorsS.J. Ko
Pages181-184
Number of pages4
Publication statusPublished - 2004 Dec 1
EventProceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004 - Seoul, Korea, Republic of
Duration: 2004 Nov 182004 Nov 19

Publication series

NameProceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004

Other

OtherProceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004
CountryKorea, Republic of
CitySeoul
Period04/11/1804/11/19

Fingerprint

Biometrics
Smart cards
Power spectrum
Personal computers
Feature extraction
Websites
Ships
Textures
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Lee, H. G., Noh, S., Bae, K., Park, K. R., & Kim, J. (2004). Invariant biometric code extraction. In S. J. Ko (Ed.), Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004 (pp. 181-184). (Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004).
Lee, Hyung Gu ; Noh, Seungin ; Bae, Kwanghyuk ; Park, Kang Ryoung ; Kim, Jaihie. / Invariant biometric code extraction. Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004. editor / S.J. Ko. 2004. pp. 181-184 (Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004).
@inproceedings{905e7bb5a3fa4c6e8411df54b41225e6,
title = "Invariant biometric code extraction",
abstract = "We propose invariant key generation method using iris image. In conventional iris recognition system, iris features are not consistent because most feature extraction techniques are sensitive to the variations of captured iris image data. In this paper, we introduce the invariant binary feature which is defined as iris key. Regardless of iris image variations, we can extract the invariant iris key in our experiments. Our method can be applied to various fields especially for key protection and key management application using biometric data, which include e-commerce, smart card, and logging into personal computer or secured web site. To generate the iris key, we propose the reference pattern which is designed as lattice structured image to represent a bit pattern as individual's identity. The reference pattern and iris image are linked into filter. In the filter, iris texture is reflected according to magnitude of iris power spectrum in frequency domain. There is a trade-off relation-ship between with-in class tolerance and between-class discrimination, so that we can control these factors which are included in the filter. In experimental results, we were able to tune the system to a False Rejection Ratio(FRR) level of 1.0{\%}.",
author = "Lee, {Hyung Gu} and Seungin Noh and Kwanghyuk Bae and Park, {Kang Ryoung} and Jaihie Kim",
year = "2004",
month = "12",
day = "1",
language = "English",
isbn = "0780386396",
series = "Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004",
pages = "181--184",
editor = "S.J. Ko",
booktitle = "Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004",

}

Lee, HG, Noh, S, Bae, K, Park, KR & Kim, J 2004, Invariant biometric code extraction. in SJ Ko (ed.), Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004. Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004, pp. 181-184, Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004, Seoul, Korea, Republic of, 04/11/18.

Invariant biometric code extraction. / Lee, Hyung Gu; Noh, Seungin; Bae, Kwanghyuk; Park, Kang Ryoung; Kim, Jaihie.

Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004. ed. / S.J. Ko. 2004. p. 181-184 (Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004).

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

TY - GEN

T1 - Invariant biometric code extraction

AU - Lee, Hyung Gu

AU - Noh, Seungin

AU - Bae, Kwanghyuk

AU - Park, Kang Ryoung

AU - Kim, Jaihie

PY - 2004/12/1

Y1 - 2004/12/1

N2 - We propose invariant key generation method using iris image. In conventional iris recognition system, iris features are not consistent because most feature extraction techniques are sensitive to the variations of captured iris image data. In this paper, we introduce the invariant binary feature which is defined as iris key. Regardless of iris image variations, we can extract the invariant iris key in our experiments. Our method can be applied to various fields especially for key protection and key management application using biometric data, which include e-commerce, smart card, and logging into personal computer or secured web site. To generate the iris key, we propose the reference pattern which is designed as lattice structured image to represent a bit pattern as individual's identity. The reference pattern and iris image are linked into filter. In the filter, iris texture is reflected according to magnitude of iris power spectrum in frequency domain. There is a trade-off relation-ship between with-in class tolerance and between-class discrimination, so that we can control these factors which are included in the filter. In experimental results, we were able to tune the system to a False Rejection Ratio(FRR) level of 1.0%.

AB - We propose invariant key generation method using iris image. In conventional iris recognition system, iris features are not consistent because most feature extraction techniques are sensitive to the variations of captured iris image data. In this paper, we introduce the invariant binary feature which is defined as iris key. Regardless of iris image variations, we can extract the invariant iris key in our experiments. Our method can be applied to various fields especially for key protection and key management application using biometric data, which include e-commerce, smart card, and logging into personal computer or secured web site. To generate the iris key, we propose the reference pattern which is designed as lattice structured image to represent a bit pattern as individual's identity. The reference pattern and iris image are linked into filter. In the filter, iris texture is reflected according to magnitude of iris power spectrum in frequency domain. There is a trade-off relation-ship between with-in class tolerance and between-class discrimination, so that we can control these factors which are included in the filter. In experimental results, we were able to tune the system to a False Rejection Ratio(FRR) level of 1.0%.

UR - http://www.scopus.com/inward/record.url?scp=21444431872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21444431872&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780386396

T3 - Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004

SP - 181

EP - 184

BT - Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004

A2 - Ko, S.J.

ER -

Lee HG, Noh S, Bae K, Park KR, Kim J. Invariant biometric code extraction. In Ko SJ, editor, Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004. 2004. p. 181-184. (Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2004).