Iris Recognition using Multi-Resolution Frequency Analysis and Levenberg-Marquardt Back-Propagation

  • Published : 2004.03.01

Abstract

In this paper, we suggest an Iris recognition system with an excellent recognition rate and confidence as an alternative biometric recognition technique that solves the limit in an existing individual discrimination. For its implementation, we extracted coefficients feature values with the wavelet transformation mainly used in the signal processing, and we used neural network to see a recognition rate. However, Scale Conjugate Gradient of nonlinear optimum method mainly used in neural network is not suitable to solve the optimum problem for its slow velocity of convergence. So we intended to enhance the recognition rate by using Levenberg-Marquardt Back-propagation which supplements existing Scale Conjugate Gradient for an implementation of the iris recognition system. We improved convergence velocity, efficiency, and stability by changing properly the size according to both convergence rate of solution and variation rate of variable vector with the implementation of an applied algorithm.

Keywords

References

  1. 'Iris Recognition Technology':Gerold, O. Williams, IEEE AES Systems Magazine 1997, pp. 23-29,1997
  2. 'Efficient Iris Recognition System by Optimization of Feature Vectors and Classifiers': Lim, Shinyyoung, Kwanyong Lee, Okhwan Byeon, Taiyun Kirn, Lecture Notes of Artificial Intelligence 1886, PRICAI 2000, pp.67-176, 2000
  3. 'A Human Identification Technique Using Images of the Iris and Wavelet Transform': Boles, W. W and Boashash, IEEE Trans on Signal Processing, Vol. 46, No. 4, pp. 1185-1188, Apr. 1998 https://doi.org/10.1109/78.668573
  4. 'BIOMETRICS Personal Identification in Networked Society':Anil K. Jain, Ruud Bolle and Sharath Pankanti, 1999
  5. 'Iris Verification using reference vector and changing of haar wavelet':Mun Su, Jo, graduate of engengineering., Univ.Hong-Ik, 2000
  6. 'Study on efficient preprocessing of Iris verification',: Ung-Ju Kim, graduate of engengineering., Univ. Hong-Ik, 2000
  7. 'Multirate Digital Signal processing':N. J. Fliege, John Wiley & Sons, INC., 1994
  8. 'Learing Internal Representation by Error Backpropagation':D.E.Rumelhart,G.E. Hilton, R.J. Williams, in Parallel Distributed Processing, Vo. 1, pp. 318-362,1986
  9. D.E.Rumelhart, r.Durbin, R.Golden, and Y.Chauvin, 'Backpropagation: The Basic theory', in Backpropagation-theory, Architectures,and Application, Y.Chauvin and D.E.Rumelhart(Eds.), pp.1-34, Lawrence Erlbaum Associates, Publishers,1995
  10. http://falcon.postech.ac.kr/ipawb/demo/kiss98cs4/html/sld008.html