• Publication
  • 1990
  • Issue No. 11 - November
  • Abstract - Neural Network Techniques for Object Orientation Detection: Solution by Optimal Feedforward Network and Learning Vector Quantization Approaches
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Neural Network Techniques for Object Orientation Detection: Solution by Optimal Feedforward Network and Learning Vector Quantization Approaches
November 1990 (vol. 12 no. 11)
pp. 1107-1115

The computer-vision problem of determining object orientation from the consensus of orientations of individual symbols or marks is examined. The problem arises in automatic inspection where orientation can be detected from printed text but there is no knowledge of the content of the text. This is a high-dimensional classification problem, and there is a requirement for highly accurate detection and rapid processing. The typical multilayer threshold networks are seen as unsuitable, and the optimal Bayesian detector is derived and found to have the highly parallel structure of a feedforward network. The learning vector quantization neural network method of T. Kohonen (1988) is also applied. Experimental results, comparisons, and a complete implementation are described.

[1] D.E. Rumelhart and D. McClelland, eds.,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vols. 1-2, MIT Press, Cambridge, Mass., 1986.
[2] T. Kohonen,Self-Organization and Associative Memory. Berlin, Germany: Springer-Verlag, 1988, p. 132.
[3] R. O. Duda, and P. E. Hart,Pattern Analysis and Scene Analysis. New York: Wiley, 1973.
[4] C. W. Helstrom,Statistical Theory of Signal Detection, 2nd ed. Oxford, England: Pergamon, 1968.
[5] R. J. T. Morris, "Optimal constrained selection of a measurable subset,J. Math. Anal. Appl., vol. 70, pp. 546-562, 1979.
[6] J. H. Chou, W.-S. Hsia, and T.-Y. Lee, "On multiple objective programming problems with set functions,"J. Math. Anal. Appl., vol. 105, pp. 383-394, 1985.
[7] H. W. Corley, "Optimization theory forn-set functions,"J. Math. Anal. Appl., vol. 127, pp. 193-205, 1987.
[8] A. Wald,Sequential Analysis. New York: Wiley, 1947.
[9] F. Rosenblatt,Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Washington, DC: Spartan, 1962.
[10] M. Minsky and S. Papert,Perceptrons, 2nd ed. Cambridge, MA: MIT Press, 1988.
[11] W. Y. Huang and R. L. Lippman, "Neural net and traditional classifiers," inProc. Conf. Neural Information and Processing Systems, Denver, CO, 1987. New York: AIP Press, 1988.
[12] T. Kohonen, G. Barna, and R. Chrisley, "Statistical pattern recognition with neural networks: Benchmarking studies," inProc. IEEE Int. Conf. Neural Networks, (San Diego), 1988, pp. I:61-68.
[13] T. Pavlidis,Algorithms for Graphics and Image Processing. Rockville, MD: Computer Science Press, 1982.
[14] E. M. Reingold, J. Nievergelt, and N. Deo,Combinatorial Algorithms: Theory and Practice. Englewood Cliffs, NJ: Prentice-Hall, 1977.
[15] H. Nielsen, "Neurocomputer applications," inNeural Computers, R. Eckmiller and Malsburg, Eds. Berlin, Germany: Springer-Verlag, 1988.
[16] D. Specht, "Probabilistic neural networks for classification, mapping, and associative memory, inProc. IEEE 1988 Int. Conf. Neural Networks, July 1988, pp. 525-532, vol. 1.
[17] R. P. Lippman, "An introduction to computing with neural nets,"IEEE ASSP Msg., vol. 4, pp. 4-22, 1987.
[18] T. Kohonen, personal communication.
[19] S. I. Gass,Linear Programming, 3rd ed. New York: McGraw-Hill, 1969.

Index Terms:
symbol orientation; mark orientation; pattern recognition; character recognition; object orientation detection; optimal feedforward network; learning vector quantization; computer-vision; automatic inspection; high-dimensional classification problem; optimal Bayesian detector; parallel structure; learning vector quantization neural network; automatic optical inspection; computer vision; computerised pattern recognition; learning systems; neural nets
Citation:
R.J.T. Morris, L.D. Rubin, H. Tirri, "Neural Network Techniques for Object Orientation Detection: Solution by Optimal Feedforward Network and Learning Vector Quantization Approaches," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 11, pp. 1107-1115, Nov. 1990, doi:10.1109/34.61712
Usage of this product signifies your acceptance of the Terms of Use.