This Article 
 Bibliographic References 
 Add to: 
A Multilayered Self-Organizing Artificial Neural Network for Invariant Pattern Recognition
April 1992 (vol. 4 no. 2)
pp. 162-167

An artificial neural network that self-organizes to recognize various images presented as a training set is described. One application of the network uses multiple functionally disjoint stages to provide pattern recognition that is invariant to translations of the object in the image plane. The general form of the network uses three stages that perform the functionally disjoint tasks of preprocessing, invariance, and recognition. The preprocessing stage is a single layer of processing elements that performs dynamic thresholding and intensity scaling. The invariance stage is a multilayered connectionist implementation of a modified Walsh-Hadamard transform used for generating an invariant representation of the image. The recognition stage is a multilayered self-organizing neural network that learns to recognize the representation of the input image generated by the invariance stage. The network can successfully self-organize to recognize objects without regard to the location of the object in the image field and has some resistance to noise and distortions.

[1] K. Fukushima, "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position,"Biol. Cybern., vol. 36, pp. 193-202, 1980.
[2] K. Fukushima, S. Miyake, and T. Ito, "Neocognitron: A neural network model for a mechanism of visual pattern recognition,"IEEE Trans. Syst., Man, Cybern., vol. SMC-13, no. 5, 1983.
[3] K. Fukushima, "A neural network model for selective attention in visual pattern recognition,"Biol. Cybern., vol. 55, pp. 5-15, 1986.
[4] K. Fukushima, "Neocognitron: A hierarchical neural network capable of visual pattern recognition,"Neural Networks, vol. 1. pp. 119-130, 1988.
[5] K. Fukushima, "Cognitron: A self-organizing multilayered neural network,"Biol. Cybern., vol. 20, pp. 121-136, 1975.
[6] D. H. Hubel and T. N. Wiesel, "Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex,"J. Phys. (London), vol. 160, pp. 106-154, 1962.
[7] D. O. Hebb,Organization of Behavior. New York: Wiley, 1949.
[8] H. Burkhardt and X. Mller, "On invariant sets of a certain class of fast translation-invariant transforms,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-28, no. 5, 1980.
[9] H. J. Reitboeck and T. P. Brody, "A transformation with invariance under cyclic permutation for applications in pattern recognition,"Inform. Contr., vol. 15, pp. 130-154, 1969.
[10] M.D. Wagh and S.V. Kanctkar, "A class of translation invariant transforms,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP- 25, pp. 203-205, 1977.
[11] B. Widrow and R. Winter, "Neural nets for adaptive filtering and adaptive pattern recognition,"IEEE Comput. Mag., vol. 21, no. 3, pp. 25-39, 1988.
[12] J. I. Minnix, E. S. McVey, and R. M. Iñigo, "Modified neocognitron with position normalizing preprocessor for translation invariant shape recognition,"Int. Joint Conf. Neural Nets, vol. 1, June 1990, pp. 395-399.
[13] J. I. Minnix, "A multistaged neural network architecture for position invariant shape recognition," inProc. VCIP-90, Oct. 1990.
[14] Q. Xu, C. Y. Jurgens, B. Arrue, J. I. Minnix, B. W. Johnson, and R.M. Inigo, "A fault tolerance analysis of a neocognitron model," inProc. IJCNN-90Washington, Jan. 1990.
[15] J. I. Minnix, E. S. McVey, and R. M. Inigo, "Multistaged self-organizing neural network with biologically inspired preprocessing features for rotation and scale invariant pattern recognition," inProc. 1991 IEEE Int. Conf. Syst., Man. Cybern., Oct. 1991.

Index Terms:
multilayered self-organizing artificial neural network; invariant pattern recognition; training set; preprocessing; invariance; recognition; dynamic thresholding; intensity scaling; Walsh-Hadamard transform; computerised pattern recognition; computerised picture processing; neural nets
J.I. Minnix, E.S. McVey, R.M. Iñigo, "A Multilayered Self-Organizing Artificial Neural Network for Invariant Pattern Recognition," IEEE Transactions on Knowledge and Data Engineering, vol. 4, no. 2, pp. 162-167, April 1992, doi:10.1109/69.134253
Usage of this product signifies your acceptance of the Terms of Use.