New focus assessment method for iris recognition systems

Jain Jang, Kang Ryoung Park, Jaihie Kim, Yillbyung Lee

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

In this paper, we propose a new focus assessment method (focus method) for iris recognition systems, which combines the wavelet transform method and the SVM (support vector machine) [Vapnik, V., 1998. Statistical Learning Theory. John Wiley & Sons, NY, USA]. The wavelet-based method estimates focus values by using the ratio of high and low-frequency sub-band averages. The SVM find optimal decision boundary between focused and defocused image with image brightness and focus value as input values. The proposed method has shown distinctive advantages in terms of the following four points. First, by using the proposed wavelet-based method, it detects omni-directional high-frequency which is the characteristic of iris patterns. Second, proposed method can detect slight defocusing of images by using the average of high and low-frequency sub-bands simultaneously. Third, the SVM reduces the error rate of the wavelet-based method by finding the optimum threshold. Fourth, processing time is reduced. It is 213 times faster than the maximum speeds compared with previous spatial domain methods [Kang, B., Park, K., 2006. A study on fast iris restoration based on focus checking. In: LNCS (AMDO 2006), vol. 4069, pp. 19-28; Daugman, J.G., 2004. How iris recognition works. IEEE Trans. Circuits Systems Video Technol. 14, 21-30; Wei, Z., Tan, T., Sun, Z., Cui, J., 2005. Robust and Face Assessment of Iris Image Quality. ICB. pp. 464-471]. For making the reference criteria to compare with the result of focus measures, we propose a schematic model for evaluating the pixel size of SR (specular reflection) in the cornea. To compare with the performance rate, Daugman's kernel, Kang's kernel, Wei's kernel and Kautsky's method are tested with the proposed method using five different types of data. The proposed method showed the best performance and has shown 3.03% of ER (error rate) using the Yonsei database and 2.62% of ER using the UBIRIS.

Original languageEnglish
Pages (from-to)1759-1767
Number of pages9
JournalPattern Recognition Letters
Volume29
Issue number13
DOIs
Publication statusPublished - 2008 Oct 1

Fingerprint

Support vector machines
Schematic diagrams
Sun
Wavelet transforms
Image quality
Restoration
Luminance
Pixels
Networks (circuits)
Processing

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Jang, Jain ; Park, Kang Ryoung ; Kim, Jaihie ; Lee, Yillbyung. / New focus assessment method for iris recognition systems. In: Pattern Recognition Letters. 2008 ; Vol. 29, No. 13. pp. 1759-1767.
@article{cd515df16871499d934925d318f3ba75,
title = "New focus assessment method for iris recognition systems",
abstract = "In this paper, we propose a new focus assessment method (focus method) for iris recognition systems, which combines the wavelet transform method and the SVM (support vector machine) [Vapnik, V., 1998. Statistical Learning Theory. John Wiley & Sons, NY, USA]. The wavelet-based method estimates focus values by using the ratio of high and low-frequency sub-band averages. The SVM find optimal decision boundary between focused and defocused image with image brightness and focus value as input values. The proposed method has shown distinctive advantages in terms of the following four points. First, by using the proposed wavelet-based method, it detects omni-directional high-frequency which is the characteristic of iris patterns. Second, proposed method can detect slight defocusing of images by using the average of high and low-frequency sub-bands simultaneously. Third, the SVM reduces the error rate of the wavelet-based method by finding the optimum threshold. Fourth, processing time is reduced. It is 213 times faster than the maximum speeds compared with previous spatial domain methods [Kang, B., Park, K., 2006. A study on fast iris restoration based on focus checking. In: LNCS (AMDO 2006), vol. 4069, pp. 19-28; Daugman, J.G., 2004. How iris recognition works. IEEE Trans. Circuits Systems Video Technol. 14, 21-30; Wei, Z., Tan, T., Sun, Z., Cui, J., 2005. Robust and Face Assessment of Iris Image Quality. ICB. pp. 464-471]. For making the reference criteria to compare with the result of focus measures, we propose a schematic model for evaluating the pixel size of SR (specular reflection) in the cornea. To compare with the performance rate, Daugman's kernel, Kang's kernel, Wei's kernel and Kautsky's method are tested with the proposed method using five different types of data. The proposed method showed the best performance and has shown 3.03{\%} of ER (error rate) using the Yonsei database and 2.62{\%} of ER using the UBIRIS.",
author = "Jain Jang and Park, {Kang Ryoung} and Jaihie Kim and Yillbyung Lee",
year = "2008",
month = "10",
day = "1",
doi = "10.1016/j.patrec.2008.05.005",
language = "English",
volume = "29",
pages = "1759--1767",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "13",

}

New focus assessment method for iris recognition systems. / Jang, Jain; Park, Kang Ryoung; Kim, Jaihie; Lee, Yillbyung.

In: Pattern Recognition Letters, Vol. 29, No. 13, 01.10.2008, p. 1759-1767.

Research output: Contribution to journalArticle

TY - JOUR

T1 - New focus assessment method for iris recognition systems

AU - Jang, Jain

AU - Park, Kang Ryoung

AU - Kim, Jaihie

AU - Lee, Yillbyung

PY - 2008/10/1

Y1 - 2008/10/1

N2 - In this paper, we propose a new focus assessment method (focus method) for iris recognition systems, which combines the wavelet transform method and the SVM (support vector machine) [Vapnik, V., 1998. Statistical Learning Theory. John Wiley & Sons, NY, USA]. The wavelet-based method estimates focus values by using the ratio of high and low-frequency sub-band averages. The SVM find optimal decision boundary between focused and defocused image with image brightness and focus value as input values. The proposed method has shown distinctive advantages in terms of the following four points. First, by using the proposed wavelet-based method, it detects omni-directional high-frequency which is the characteristic of iris patterns. Second, proposed method can detect slight defocusing of images by using the average of high and low-frequency sub-bands simultaneously. Third, the SVM reduces the error rate of the wavelet-based method by finding the optimum threshold. Fourth, processing time is reduced. It is 213 times faster than the maximum speeds compared with previous spatial domain methods [Kang, B., Park, K., 2006. A study on fast iris restoration based on focus checking. In: LNCS (AMDO 2006), vol. 4069, pp. 19-28; Daugman, J.G., 2004. How iris recognition works. IEEE Trans. Circuits Systems Video Technol. 14, 21-30; Wei, Z., Tan, T., Sun, Z., Cui, J., 2005. Robust and Face Assessment of Iris Image Quality. ICB. pp. 464-471]. For making the reference criteria to compare with the result of focus measures, we propose a schematic model for evaluating the pixel size of SR (specular reflection) in the cornea. To compare with the performance rate, Daugman's kernel, Kang's kernel, Wei's kernel and Kautsky's method are tested with the proposed method using five different types of data. The proposed method showed the best performance and has shown 3.03% of ER (error rate) using the Yonsei database and 2.62% of ER using the UBIRIS.

AB - In this paper, we propose a new focus assessment method (focus method) for iris recognition systems, which combines the wavelet transform method and the SVM (support vector machine) [Vapnik, V., 1998. Statistical Learning Theory. John Wiley & Sons, NY, USA]. The wavelet-based method estimates focus values by using the ratio of high and low-frequency sub-band averages. The SVM find optimal decision boundary between focused and defocused image with image brightness and focus value as input values. The proposed method has shown distinctive advantages in terms of the following four points. First, by using the proposed wavelet-based method, it detects omni-directional high-frequency which is the characteristic of iris patterns. Second, proposed method can detect slight defocusing of images by using the average of high and low-frequency sub-bands simultaneously. Third, the SVM reduces the error rate of the wavelet-based method by finding the optimum threshold. Fourth, processing time is reduced. It is 213 times faster than the maximum speeds compared with previous spatial domain methods [Kang, B., Park, K., 2006. A study on fast iris restoration based on focus checking. In: LNCS (AMDO 2006), vol. 4069, pp. 19-28; Daugman, J.G., 2004. How iris recognition works. IEEE Trans. Circuits Systems Video Technol. 14, 21-30; Wei, Z., Tan, T., Sun, Z., Cui, J., 2005. Robust and Face Assessment of Iris Image Quality. ICB. pp. 464-471]. For making the reference criteria to compare with the result of focus measures, we propose a schematic model for evaluating the pixel size of SR (specular reflection) in the cornea. To compare with the performance rate, Daugman's kernel, Kang's kernel, Wei's kernel and Kautsky's method are tested with the proposed method using five different types of data. The proposed method showed the best performance and has shown 3.03% of ER (error rate) using the Yonsei database and 2.62% of ER using the UBIRIS.

UR - http://www.scopus.com/inward/record.url?scp=48649093382&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48649093382&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2008.05.005

DO - 10.1016/j.patrec.2008.05.005

M3 - Article

AN - SCOPUS:48649093382

VL - 29

SP - 1759

EP - 1767

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 13

ER -