대한전기학회논문지:시스템및제어부문D (The Transactions of the Korean Institute of Electrical Engineers D)

대한전기학회 (The Korean Institute of Electrical Engineers)
권호 표지

2D wavelet과 이차신경망을 이용한 패턴인식 시스템

A Pattern Recognition System Using 2D Wavelets and Second-Order Neural Networks

  • 발행 : 2001.10.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Image processings using the two-dimensional wavelet transform (2DWT) have been a very active research area in recent years because the 2DWT possess many good properties. However, the discrete 2DWT can not be used for pattern recognition directly because it does not have the translation property. In this paper, we show why conventional discrete two-dimensional wavelet transforms cannot be used for pattern recognitions directly. Then, we propose a new method that makes it possible to use discrete 2DWT to pattern recognition without modification of standard pyramidal algorithms. The main idea of our method is to postprocess the wavelet transformed images using the second-order neural network. To justify the validity of the method, evaluations with test images were performed. The effectiveness of the method can be shown by the evaluation results.

키워드

참고문헌

  1. M. Vetterli, 'A theory of multirate filter banks,' IEEE Trans.on ASSP, vol. 35, no. 3, pp. 356-372, Mar., 1987 https://doi.org/10.1109/TASSP.1987.1165137
  2. S. G. Mallat, 'A theory for multiresolution signal decomposition:The wavelet representation,' IEEE Trans.on PAMI, vol. 11, no. 7, pp. 674-693, July, 1989 https://doi.org/10.1109/34.192463
  3. S.G. Mallat, 'Multifrequency Channel decompositions of images and wavelet models,' IEEE Trans.on ASSP, vol. 37, no. 12, pp. 2091-2109, Dec., 1989 https://doi.org/10.1109/29.45554
  4. I. Daubechies, 'Orthnormal bases of compactly supported wavelets,' Commun. Pure Appl. Math., vol. 41, pp. 909-996, Nov., 1988 https://doi.org/10.1002/cpa.3160410705
  5. J. Liang and T.W. Parks, 'Image Coding Using Translation Invariant Wavelet Transforms with Symmetric Extensions,' IEEE Trans.on Image Processing, vol. 7, no. 5, pp. 762-768, May, 1998 https://doi.org/10.1109/83.668030
  6. G. G. Walter, 'Translation and dilation invariance in orthogonal wavelets,' Applied & Computational Harmonic Analysis, vol 1, pp. 344-349, 1994 https://doi.org/10.1006/acha.1994.1020
  7. E. P. Simoncelli, W. T. Freeman and D.J. Heeger, 'Shiftable multiscale transforms,' IEEE Trans.Information theory, vol. 38, pp. 587-607, Mar., 1992 https://doi.org/10.1109/18.119725
  8. S. G. Mallat, S. Zhong, 'Characterisation of signals from multiscale edges,' , IEEE Trans.on PAMI, vol. 14, no. 7, pp. 710-732, July, 1992 https://doi.org/10.1109/34.142909
  9. S. D. Macro, P. Heller and J. Weiss, 'An M-band,2-dimensional translation-invariant wavelet transform and applications,', Proceeding of ICASSP, pp. 1077-1080, 1995 https://doi.org/10.1109/ICASSP.1995.480421
  10. I. Cohen, S. Raz, D. Malah, 'Shift invariant wavelet packet bases,' Proceeding of ICASSP, pp. 1081-1084, 1995
  11. J. Liang and T. W. Parks, 'A translation invariant wavelet representation algorithm and its application,' IEEE Trans. on Signal processing, vol. 44, pp. 225-232, Feb., 1996 https://doi.org/10.1109/78.485919
  12. 이봉규, 조유근, '입력차원 축소를 이용한 이동 불변2차신경망의 효율적 구현,' 정보과학회 논문지, 제21권, 제12호, pp. 2383-2389, 1994
  13. B. Lee, S. Cho and Y. Cho, 'Translation,scale and rotation invariant pattern recognition using PCA and reduced second-order neural network,' Int'l Journal of Neural, Parallel and Scientific Computation, vol. 3, no. 3, pp. 417-429, 1995
  14. A. Grossmann, J. Morlet, 'Decomposition of Hardy functions into square integrable wavelets of constant shape,' SIAM J.Math., Vol. 15, pp. 723-736, 1984 https://doi.org/10.1137/0515056
  15. R. K. Young, Wavelet theory and its application, Kluwer Academic Publishers, 1993.
  16. M. J. Shensa, 'The discrete wavelet transform:Wedding the a Trous and Mallat algorithm,' IEEE Trans.on Signal Processing, vol. 40, pp. 2464-2482, Oct., 1992 https://doi.org/10.1109/78.157290
  17. M. Antonini, M. Barlaud, P. Mathieu, and I. Daubechies, 'Image coding using the wavelet transform,' IEEE Trans.on Image Processing, vol. 1, no. 2, pp. 205-220, 1992 https://doi.org/10.1109/83.136597
  18. R. H. Bamberger, S. L. Eddins, V. Nui, 'Generalized symmetric extensions for size limited multirate filter banks,' IEEE Trans.on Image Processing, vol. 3, no. 1, pp. 82-87, Jan., 1994 https://doi.org/10.1109/83.265983
  19. G. Pirani, V. Zingarelli, 'Analytical formula for design of quadrature mirror filters,', IEEE Trans.on ASSP, vol. 32, no. 6, pp. 645-648, June, 1984
  20. J. W. Woods, S. D. O'Neil, 'Subband coding of images,' IEEE Trans.on ASSP, vol. 34, no. 5, pp. 1278-1288, Oct., 1986 https://doi.org/10.1109/TASSP.1986.1164962
  21. M. Antonini, T. Gaidon, P. Mathieu and M. Barlaud. Wavelet transform and image coding.Wavelets in Image Communication. pp. 65-111, Elsevier. 1994
  22. C. L. Giles, T. Maxwell, 'Learning invariance,and generalization in high-order neural networks,' Applied Optics, vol. 26, pp. 2972-2978, 1987
  23. W. A. C. Schmidt, J.P. Davis, 'Pattern Recognition Properties of various feature spaces for higher order Neural Networks,' IEEE Transaction on PAMI, vol. 15, no. 8, pp. 795-801, Aug., 1993 https://doi.org/10.1109/34.236250
  24. Y. Xu, J. Weaver, D. Healy and J. Ju, 'Wavelet transform domain filters:A spatially selective noise filteration technique,' IEEE Trans.on Image Processing, vol. 3, no. 6, pp. 747-758 https://doi.org/10.1109/83.336245