论文信息 - Comparison of artificial neural networks with pattern recognition and image processing.

Comparison of artificial neural networks with pattern recognition and image processing.

This paper presents a comparison between the field of artificial neural network and the field of image processing and pattern recognition. It shows that some of the adaptive processing algorithms for pattern recognition and image processing, in terms of neural networks, can be seen as adaptive heteroassociative and autoassociative memories, respectively. The similarities and differences between these two fields are addressed.

[1] Dante C. Youla,et al. Generalized Image Restoration by the Method of Alternating Orthogonal Projections , 1978 .

[2] J J Hopfield,et al. Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[3] James R. Leger,et al. Optical implementation of the least-squares linear mapping technique for image classification , 1982 .

[4] J. Goodman,et al. Neural networks for computation: number representations and programming complexity. , 1986, Applied optics.

[5] D Psaltis,et al. Optical implementation of the Hopfield model. , 1985, Applied optics.

[6] James R. Leger,et al. IMAGE CLASSIFICATION BY AN OPTICAL IMPLEMENTATION OF THE FUKUNAGA-KOONTZ TRANSFORM. , 1982 .

[7] J. Cadzow,et al. An extrapolation procedure for band-limited signals , 1979 .

[8] David Zipser,et al. Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[9] Takayuki Ito,et al. Neocognitron: A neural network model for a mechanism of visual pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[10] Stephen Grossberg,et al. A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..