Abstract
The use of a massively parallel neural array for multiple 2-D object recognition is explored. The array architecture has a parallel modular form with each module being trained over a specific object class. One test bed is developed using alphabetic characters which have been subjected to a scale factor and rotational operations. This test bed provides a simultaneous measure of geometric invariance and of character recognition. The performance of the modular design is benchmarked against a backprop-trained multilayer perceptron network of equivalent generality. A second test of the modular array is conducted using TV and FLIR images. This second evaluation assesses the ability to extract obejct signatures from a clutter background.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Fukushima, S. Miyake, and T. Ito, “Neocognitron: A Neural Network Model for a Mechanism of Visual Pattern Recognition,”Neurocomputing, pp. 526–534, 1988.
D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning Internal Representations by Error Propagation,” inParallel Distributed Processing, vol. 1 (D.E. Rumelhart and J.L. McClelland, eds.), Cambridge, MA: MIT Press, 1986, Chap. 8.
J. Sietsma and R. Dow, “Creating Artificial Neural Networks That Generalize,”Neural Networks, vol. 4, pp. 67–79, 1991.
C.L. Giles, and T. Maxwell, “Learning, Invariance, and Generalization in High-Order Neural Networks,”App. Opt., vol. 26, No. 23, pp. 4972–4978, 1987.
D. Psaltis, J. Hong, and S. Venkatesh, “Shift Invariance in Optical Associative Memories,”Proc. Soc. Photo-Opt. Instrum. Eng., vol. 625, p. 189, 1986.
W.A. Porter and S. Ligade, “Training the Higher Order Moment Neural Array,”IEEE Trans Signal Processing, July, 1994.
A. Khotanzad and J.H. Lu, “Distortion Invariant Recognition by a Multi-Layer Perceptron and Back-Propagation Learning,” inIEEE Int. Conf. Neural Networks, Vol. 1, pp. 625–632, 1988.
Jon Kennedy and Piero Morasso, “Self-Organizing Networks in Handwriting Analysis,” inSecond Italian Workshop on Parallel Architectures and Neural Networks, World Scientific, pp. 339–344, 1990.
I. Guyon, P. Albrecht, Y. Le Cun, J. Denker, and W. Hubbard, “Design of a Neural Network Character Recognizer for a Touch Terminal,”Pattern Recognition, vol. 24, no. 2, pp. 105–119, 1991.
C. Youn and S. Kak, “New Learning and Control Algorithms for Neural Networks,” inAdvances in Communications and Control Systems, Berlin and New York: Springer-Verlag, 1989.
J.J. Hopfield, et al., “Unlearning has a Stabilizing Effect in Collective Memories,”Naturem, vol. 304, pp. 158–159, 1983.
W.A. Porter, “Neuromic Arrays: Design and Performance,” inProc. WNN-AIND 91, Auburn Univ., 1991.
W.A. Porter, “Using Polynomic Embedding for Neural Network Design,”IEEE Trans Circuits Systems, vol. 39, no. 6, 1992.
W.A. Porter, and S. Ligade, “Extending Memory in the Neuromic Array,” inProc. IEEE SoutheastCon '92, Birmingham, AL, 1992.
J.M. Mendel, “Tutorial on Higher-Order Statistics in Signal Processing and System Theory,”Proc. IEEE, vol. 79, no. 3, 1991.
M.K. Tsatianis and G.B. Granuakis, “Object and Texture Classification Using Higher Order Statistics,”IEEE Trans. PAMI, vol. 14, no. 7, 1992.
Yajun Li, “Performing the Theory of Invariant Moments for Pattern Recognition,”Pattern Recognition, vol. 25, no. 7, pp. 723–730, 1992.
S.O. Belkasin, M. Shridhar, and M. Ahmadi, “Pattern Recognition with Moment Invariants: A Comparative Study and New Results,”Pattern Recognition, vol. 24, no. 12, pp. 1117–1138, 1991.
P. Flandrin and O. Rioul, “Affine Smoothing of the Wigner-Ville Distribution,” inProc. Int. Conf. ASSP, pp. 2455–2458, 1990.
S. Kadambe, G.F. Boudreau-Bartels, and P. Dusant, “Window Length Selection for Smoothing the Wigner Distribution,”Proc. ICASSP '89, pp. 2226–2229, 1989.
W.A. Porter, “Synthesis of Polynomic Systems,”SIAM J. Appl. Math., vol. 11, no. 2, 1980.
W. Greub,Multilinear Algebra, New York: Springer-Verlag, 1978.
W.A. Porter, “Multiple Signal Extraction by Polynomic Filtering,”J. Math. System Theory, vol. 13, pp. 237–254, 1980.
W.A. Porter, “Comparative Performance of Polynomic Signal Extraction,”Circuits, Systems, Signal Proc., vol. 1, no. 1, 1982.
W.A. Porter, “Recent Advances in Neural Arrays,” Special Issue:Networks for Neural Processing, Circuits Systems Signal Process., vol. 12, no. 2, 1993.
W.A. Porter and W. Liu, “Auxiliary Computations for Neural Networks,”Circuits, Systems, and Signal Processing, (submitted).
W.A. Porter and W. Liu, “Alphabet Character Recognition with a Generalizing Neural Network,” inProc. First Int. Conf., Fuzzy Theory and Technology, Durham, NC, 1992.
G. Wilensky, “Analysis of Neural Network Issues: Scaling, Enhanced Nodal Processing, Comparison with Standard Classification,” inDARPA Neural Network Program Review, Oct. 29–30, 1990.
G. Carpenter, S. Grossberg, et al., “Fuzzy ARTMAP.”IEEE Trans. Neural Networks, vol. 3, no. 5, 1992.
R. Schalkoff,Pattern Recognition, New York: Wiley, 1992.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Porter, W.A., Liu, W. Object recognition by a massively parallel 2-D neural architecture. Multidim Syst Sign Process 5, 179–201 (1994). https://doi.org/10.1007/BF00986977
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00986977