Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Robust iris recognition for local noise based on wavelet transforms

국부잡음에 강인한 웨이블릿 기반의 홍채 인식 기법

  • Park Jonggeun (Department of electrical and electronic Engineering, Yonsei University) ;
  • Lee Chulhee (Department of electrical and electronic Engineering, Yonsei University)
  • 박종근 (연세대학교 전기전자공학과) ;
  • 이철희 (연세대학교 전기전자공학과)
  • Published : 2005.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a feature extraction method for iris recognition using wavelet transforms. The wavelet transform is fast and has a good localization characteristic. In particular, the low frequency band can be used as an effective feature vector. In iris recognition, the noise caused by eyelid the eyebrow, glint, etc may be included in iris. The iris pattern is distorted by noises by itself, and a feature extraction algorithm based on filter such as Wavelets, Gabor transform spreads noises into whole iris region. Namely, such noises degrade the performance of iris recognition systems a major problem. This kind of noise has adverse effect on performance. In order to solve these problems, we propose to divide the iris image into a number of sub-region and apply the wavelet transform to each sub-region. Experimental results show that the performance of proposed method is comparable to existing methods using Gabor transform and region division noticeably improves recognition performance. However, it is noted that the processing time of the wavelet transform is much faster than that of the existing methods.

본 논문에서는 웨이블릿 변환을 이용하여 흥채의 특징을 추출하는 기법에 대해 제안한다. 웨이블릿 변환은 수행 속도가 빠르며 신호의 에너지를 저주파 대역으로 잘 모아주는 우수한 국소화 특징을 갖고 있으며, 특히 저주파 대역을 효율적인 특징 벡터로 사용한 수 있다. 한편 인식에 사용하고자 하는 흥채 영역에 눈꺼풀, 눈썹, 반사광, 안경의 흠집 등으로 인한 잡음이 포함될 수 있다. 이러한 잡음은 그 자체로도 홍채 패턴을 크게 변형시키며, 웨이블릿, 가보 등의 필터 기반 특징 추출 알고리즘은 잡음을 전체 영역으로 확산시킨다. 즉 잡음은 흥채 인식 시스템의 성능을 저하시킨다. 이를 막기 위해 본 논문에서는 홍채 템플릿을 여러 개의 영역으로 분할하여 각 영역에 대해 웨이블릿 변환을 수행함으로써 잡음의 영향을 제한된 영역에 국한시킨다. 실험에서 웨이블릿 방법이 기존의 Gabor 변환을 이용한 특징 추출 방법과 비교하여 특징 추출 속도는 더 빠르면서 대등한 성능을 보여주는 것을 확인할 수 있으며 영역 분할로 인해 성능 개선이 되었다.

Keywords

References

  1. Arun Ross, Anil Jain, 'Information fusion in biometrics,' Pattern Recognition Letters, Vol.24, pp.2115-2125, 2003 https://doi.org/10.1016/S0167-8655(03)00079-5
  2. Gerald O. Williams, 'Iris Recognition technology,' Aerospace and Electronic Systems Magazine, IEEE, vol. 12, no. 4, pp. 23-29, April 1997 https://doi.org/10.1109/62.575997
  3. Samir Nanavati, Michael Theme, Raj Nanavati, 'Biometrics identity verification in a networked world'
  4. D. de Martin-Roche, C. Sanchez-Avila, R. Sanchez-Reillo, 'Iris recognition for biometric identification using dyadic wavelet transform zero-crossing,' Security Technology, 2001 IEEE 35th International Carnahan Conference on, pp. 272-277, 16-19 Oct 2001 https://doi.org/10.1109/.2001.962844
  5. Va-Ping Huang, Si-Wei Luo, En-Yi ChenAn, 'Efficient iris recognition system,' Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on, pp. 450-454, 4-5 Nov. 2002 https://doi.org/10.1109/ICMLC.2002.1176794
  6. John G. Daugman, 'How Iris Recognition Works,' IEEE Transactions on Circuits and Systems for Video Technology, Vol.14, No.1, pp.21-29, Jan., 2004 https://doi.org/10.1109/TCSVT.2003.818350
  7. Daugman, J. 'High confidence recognition of persons by iris patterns,' Security Technology, 2001 IEEE 35th International Carnahan Conference on, pp. 254-263, 16-19 Oct. 2001 https://doi.org/10.1109/.2001.962841
  8. Daugman, J. 'High confidence personal identification by rapid video analysis of iris texture,' Security Technology, 1992. Crime Countermeasures, Proceedings. Institute of Electrical and Electronics Engineers 1992 International Carnahan Conference on, pp. 50-60, 14-16 Oct. 1992 https://doi.org/10.1109/CCST.1992.253755
  9. Daugman, J, Downing, C, 'Recognizing iris texture by phase demodulation,' Image Processing for Biometric Measurement, IEE Colloquium on, pp. 1-8, 20 Apr 1994
  10. Wildes, R.P, 'Iris recognition: an emerging biometric technology,' Proceedings of the IEEE, vol. 85, no. 9, pp. 1348-1363, Sept. 1997 https://doi.org/10.1109/5.628669
  11. Wildes, R.P, Asmuth, J.C, Green, G.L, Hsu, S.C, Kolczynski, R.J, Matey, J.R, McBride, S.E, 'A system for automated iris recognition,' Applications of Computer Vision, 1994., Proceedings of the Second IEEE Workshop on, pp. 121-128, 5-7 Dec. 1994 https://doi.org/10.1109/ACV.1994.341298
  12. Boles, W.W, Boashash, B, 'A human identification technique using images of the iris and wavelet transform,' Signal Processing, IEEE Transactions on, pp. 1185- 1188, April 1998 https://doi.org/10.1109/78.668573
  13. Boles, W.W, 'A security system based on human iris identification using wavelet transform,' Knowledge-Based Intelligent Electronic Systems, 1997. KES '97. Proceedings., 1997 First International Conference on, vol. 2, pp. 533-541, 21-23 May 1997 https://doi.org/10.1109/KES.1997.619433
  14. Boles, W.W, 'A Wavelet Transform Based Technique For The Recognition Of The Human Iris,' Signal Processing and Its Applications, 1996. ISSPA 96., Fourth International Symposium on, pp. 601-604, 25-30 August 1996
  15. Unser, M, 'Splines : a perfect fit for signal and image processing,' Signal Processing Magazine, IEEE, vol. 16, no. 6, pp. 22-38, Nov. 1999 https://doi.org/10.1109/79.799930
  16. R. G. Key, 'Cubic Convolution Interpolation for Digital Image Processing,' IEEE Transactions on Acoustics, speech, and signal processing, pp. 1153-1160, 1981 https://doi.org/10.1109/TASSP.1981.1163711
  17. M. Vetterli and J. Kovacevic, 'Wavelets and Subband Coding,' Prentice Hall, 1995
  18. Gilbert Strang, Truong Nguyen, 'Wavelets and Filter Banks,'Wellesley_Cambridge Press, 1995
  19. S. G. Mallet, 'A theory of multiresolution signal decomposition: the wavelet representation', IEEE Trans. on Pattern Recognition and Machine Intelligence, Vol. 11, No.7, pp. 674-693, July 1989 https://doi.org/10.1109/34.192463