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

대한전기학회 (The Korean Institute of Electrical Engineers)
권호 표지

패턴인식을 위한 일반화된 이차신경망 구현

An Implementation of Generalized Second-Order Neural Networks for Pattern Recognition

  • 이봉규 (제주대학교 전산통계학과) ;
  • 양요한 (제주대학교 전산통계학과)
  • 발행 : 2002.10.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

For most of pattern recognition applications, it is required to correctly recognize patterns even if they have translation variations. In this paper, to achieve the goal of translation invariant pattern recognition, we propose a new generalized translation invariant second-order neural network using a constraint on the weights. The weight constraint is implemented using generalized translation invariant features which are accumulated sums of pixel combinations. Simulation results will be given to demonstrate that the proposed second-order neural network has the generalized translation invariant property.

키워드

참고문헌

  1. S.E. Palmer, Reference Frames in the perception of shape and orientation, Object Perception, pp. 121-163, 1989
  2. R. L. Kashyap, R. Chellappa, Stochastic models for closed boundary analysis: representation and reconstruction, IEEE Trans on Information Theory, vol. 27, pp. 627-637, 1981 https://doi.org/10.1109/TIT.1981.1056390
  3. T.R. Crimmins, A complete set of Fourier descriptors for two-dimensional shapes, IEEE Trans. on System, Man and Cybernetics, vol. 12, pp. 848-855, 1982 https://doi.org/10.1109/TSMC.1982.4308918
  4. G.P.R. Savarayudu, I.K. Sethi, Walsh descriptor for polygonal curves, Pattern Recognition, vol. 16, pp. 848-855, 1983
  5. S. O. Belkasim, M. Shridhar, M. Ahmadi, Pattern recognition with moment invariants: a comparative study and new results, Pattern Recognition, vol. 24, pp. 1117-1138, 1991 https://doi.org/10.1016/0031-3203(91)90140-Z
  6. H. Wechsler, G.L. Zimmerman, 2-D invariant object recognition using distributed associative memory, IEEE Trans. on PAMI, vol. 10, pp. 811-821, 1988 https://doi.org/10.1109/34.9104
  7. K. Fukushima, Neocognitron: A hierarchical neural network capable of visual pattern recognition, Neural Networks, vol. 1, pp. 119-130, 1988 https://doi.org/10.1016/0893-6080(88)90014-7
  8. K. Fukushima, Analysis of the process of visual recognition by the Neocognitron, Neural Networks, vol. 2, pp. 413-420, 1989 https://doi.org/10.1016/0893-6080(89)90041-5
  9. E. Barnard, D. Casasent, Shift invariance and the Neocognitron, Neural Networks, vol. 3, pp. 403-410, 1990 https://doi.org/10.1016/0893-6080(90)90023-E
  10. B. Widrow, R.G. Winter, R.A. Baxter, Layered neural nets for pattern recognition, ASSP, vol. 36, pp. 1109-1118, 1988 https://doi.org/10.1109/29.1638
  11. A. Khotanzad, J.H. Lu, Classification of invariant image representations using a neural network, ASSP, vol. 38, pp. 1028-1038, 1990 https://doi.org/10.1109/29.56063
  12. B. Yegnanarayana, A. Ravichandran, A two stage neural network for translation, rotation and size invariant pattern recognition, Proc. of ICASSP91, 1991
  13. A. Hasegawa, K. Itoh, Y. Ichioka, Generalization of shift invariant neural networks: Image processing of corneal endothelium, Neural Networks, vol. 9, pp. 345-356, 1996 https://doi.org/10.1016/0893-6080(95)00054-2
  14. W. G. Lin, S.S. Wang, A new neural model for invariant pattern recognition, Neural Networks, vol. 9, pp. 899-913, 1996 https://doi.org/10.1016/0893-6080(95)00031-3
  15. J. I. Minnix, S. Eugene, R.M. Inigo, A multilayered self-organizing artificial neural network for invariant pattern recognition, IEEE Trans. on Knowledge and Data Engineering, vol. 4, pp. 162-167, 1992 https://doi.org/10.1109/69.134253
  16. G. A. Carpenter, S. Grossberg, Invariant pattern recognition and recall by an attentive self-organizing ART architecture in a non-stationary world, Proc. ICNN87, 1987
  17. N. Srinivasa, M. Jouaneh, A Neural network model for invariant pattern recognition, IEEE trans. on Signal Processing, vol. 40, pp. 1595-1599, 1992 https://doi.org/10.1109/78.139270
  18. M. Fukumi, S. Omatu, F. Takada, T. Kosaka, Rotation invariant neural pattern recognition system with application to coin recognition, IEEE Trans. on Neural Networks, vol. 3, pp. 272-279, 1992 https://doi.org/10.1109/72.125868
  19. N. Srinivasa, M. Jouaneh, An invariant pattern recognition machine using a modified ART architecture, IEEE Trans. on System, Man and Cybernetics, vol. 23, pp. 1432-1437, 1993 https://doi.org/10.1109/21.260674
  20. C.L. Giles, T. Maxwell, Learning, invariance, and generalization in high-order neural networks, Applied Optics, vol. 26, pp. 2972-2978, 1987
  21. L. Spirkovska, M. B. Reid, Position, scale and rotation invariant object recognition using higher-order neural networks, Pattern Recognition, vol. 25, no. 9 pp. 957-985, 1992
  22. L. Spirkovska, M. B. Reid, Coarse-coded higher-order neural networks for PSRI object recognition, IEEE Trans. on Neural Networks, vol. 4, no. 2 pp. 276--283, 1993 https://doi.org/10.1109/72.207615
  23. B.K. Lee, H.H Lee, D.K. Kim, Y. Cho, H.Y. Hwang, Reduction of input nodes for shift invariant second-order neural networks using PCA, Proc. of ICANN94, vol. 2, pp. 1029-1032, 1994
  24. B. Lee, S. Cho, Y. Cho, Translation, scale and rotation invariant pattern recognition using PCA and reduced second-order neural network, Int. Journal of Neural, Parallel and Scientific Computation, vol. 3, no. 3, pp. 417-429, 1995
  25. H.Y. Kwon, B.C. Kim, H.Y. Hwang, Rotation and scale invariant pattern recognition using complex log mapping and augmented second-order neural network, IEE Electronics Letters, vol. 29, no. 7, pp. 620-621, 1992
  26. W.A.C. Schmidt, J.P. Davis, Pattern recognition properties of various feature spaces for higher order neural networks, IEEE Trans. on PAMI, vol. 15, no. 8, pp. 795-801, 1993 https://doi.org/10.1109/34.236250