Invariant pattern classification neural network versus FT approach
作者： A. Dobnikar , J. Ficzko , D. Podbregar , U. Rezar
DOI: 10.1016/0165-6074(92)90018-3
关键词: Artificial neural network 、 Computer vision 、 Computer science 、 Fourier transform 、 Pattern recognition 、 Magnification 、 Normalization (image processing) 、 Invariant (mathematics) 、 Neural network modeling 、 Artificial intelligence 、 Image processing 、 Associative property
摘要: Abstract Invariant Pattern Classification (IPC) of black and white images is studied in two directions. Classical Fourier Transform (FT) approach consists normalisation procedure for excluding magnification or size influence FT transformation, whose output spectrum descriptors are invariant to rotation and/or translation. Only pattern classification independent concerned this paper. It supposed that the observed object placed center image. An alternative uses Neural Network Modeling (NNM) achieve same effect. shown proposed with combination dynamic associative properties better solves problem additional potential capability considerable higher parallel processing.
elsevier.com
sci-hub.se 参考文章(19)
J. Austin, ADAM: an associative neural architecture for invariant pattern classification international conference on artificial neural networks. pp. 196- 200 ,(1989)
Yoh-Han Pao, Adaptive pattern recognition and neural networks ,(1989)
J. J. Hopfield, D. W. Tank, Neural computation of decisions in optimization problems Biological Cybernetics. ,vol. 52, pp. 141- 152 ,(1985) , 10.1007/BF00339943
Eric L. Schwartz, Computational anatomy and functional architecture of striate cortex: A spatial mapping approach to perceptual coding Vision Research. ,vol. 20, pp. 645- 669 ,(1980) , 10.1016/0042-6989(80)90090-5
Teuvo Kohonen, Self-Organization and Associative Memory ,(1984)
Warren S. McCulloch, Walter Pitts, A logical calculus of the ideas immanent in nervous activity Bulletin of Mathematical Biology. ,vol. 52, pp. 99- 115 ,(1990) , 10.1007/BF02478259
Michael Seibert, Allen M. Waxman, Spreading activation layers, visual saccades, and invariant representations for neural pattern recognition systems Neural Networks. ,vol. 2, pp. 9- 27 ,(1989) , 10.1016/0893-6080(89)90012-9
Kunihiko Fukushima, Analysis of the process of visual pattern recognition by the neocognitron Neural Networks. ,vol. 2, pp. 413- 420 ,(1989) , 10.1016/0893-6080(89)90041-5
A.C.C. Coolen, F.W. Kuijk, A learning mechanism for invariant pattern recognition in neural networks Neural Networks. ,vol. 2, pp. 495- 506 ,(1989) , 10.1016/0893-6080(89)90046-4
L. R. Rabiner, B. Gold, C. K. Yuen, Theory and application of digital signal processing ,(1975)