Applied Intelligence

, Volume 18, Issue 2, pp 195–213 | Cite as

Image Processing Using RBF like Neural Networks: A ZISC-036 Based Fully Parallel Implementation Solving Real World and Real Complexity Industrial Problems

  • Kurosh Madani
  • Ghislain de Trémiolles
  • Pascal Tannhof

Abstract

The present article concerns neural based image processing and solutions developed for industrial problems using the ZISC-036 neuro-processor, an IBM hardware processor which implements the Restricted Coulomb Energy algorithm (RCE) and the K-Nearest Neighbor algorithm (KNN). The developed neural based techniques have been applied for image enhancement in order to restore old movies (noise reduction, focus correction, etc.), to improve digital television images, or to treat images which require adaptive processing (medical images, spatial images, special effects, etc.). We also have developed and implemented on ZISC-036 neuro-processor, a neural network based solution for visual probe mark inspection in VLSI production for the IBM Essonnes plant. The main characteristics of such systems are real-time control and high reliability in detection and classification tasks. Experimental results, validating presented concepts, have been reported showing quantitative and qualitative improvement as well as the efficiency our solutions.

image processing neural networks ZISC-036 neuro-processor real-time processing industrial application 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    L.M. Reyneri, “Weighted radial basis functions for improved pattern recognition and signal processing,” in Neural Processing Letters, vol. 2, no.3, pp 2–6, 1995.Google Scholar
  2. 2.
    G. Mercier, K. Madani, and S. Duchesne, “A specific algorithm for a restricted coulomb energy network used as a dynamical process identifier,” in RI 95, Academy Institute of Sciences, St. Petersburg, Russia, May 1995.Google Scholar
  3. 3.
    Robert David, Erin Williams, Ghislain de Trémiolles, and Pascal Tannhof, “Noise reduction and image enhancement using a hardware implementation of artificial neural networks,” VI-DYNN’98-Virtual Intelligence—Dynamic Neural Networks Stockholm-Sweden-June 22–26, 1998.Google Scholar
  4. 4.
    A. Eide, Th. Lindblad, C.S. Lindsey, M. Minerskjöld, G. Sekhviaidze, and G. Székely, “An Implementation of the zero instruction set computer (ZISC-036) on a PC/ISA-bus card,” in 1994 WNN/FNN in Washington D.C., December 1994.Google Scholar
  5. 5.
    ZISC-036 Data Book, IBM Microelectronics, November 1994.Google Scholar
  6. 6.
    ZISC/ISA ACCELERATOR card for PC, User Manual, IBM France, February 1995.Google Scholar
  7. 7.
    ZISC (Zero Instruction Set Computer), http://www.fr.ibm.com/france/cdlab/zisc.htm, IBM France, January 1998.Google Scholar
  8. 8.
    ZISC ISA and PCI Cards for IBM Compatible PC User's Manual 1.2, http://www.fr.ibm.com/france/cdlab/zisc.htm, IBM France, May 1998.Google Scholar
  9. 9.
    ZISC User's Manual, http://www.fr.ibm.com/france/cdlab/zisc.htm, IBM France, May 1998.Google Scholar
  10. 10.
    G. De Tremiolles, Contribution à l’étude théorique des modéles neuromimétiques et à leur validation expérimentale: mise enoeuvre d'applications industrielles (“Contribution to the theoretical study of neuromimetic models and to their experimental validation: use in industrial applications”), Ph.D. Report, University of PARIS XII–Val de Marne, March 1998.Google Scholar
  11. 11.
    Robert David, Erin Williams, Ghislain de Trémiolles, and Pascal Tannhof, “Description and practical uses ofIBMZISC-036,” VIDYNN’98-Virtual Intelligence—Dynamic Neural Networks Stockholm, Sweden, June 22–26, 1998.Google Scholar
  12. 12.
    I. Rojas, O. Valuenzuela, and A. Prieto, “Statistical analysis of the main parameters in the definition of radial basis function networks,” IWANN’97, Springer, Lanzarote, Canary Islands, Spain, June 4–6, 1997, pp. 882–891.Google Scholar
  13. 13.
    J.M. Moreno, J. Madrenas, S. san Anselmo, F. Castillo, and J. Cabestany, “Digital hardware implementation of ROI incremental algorithms,” in From natural to artificial neural computation, LNCS vol. 930, Springer Verlag, 1995, pp. 761–770.Google Scholar
  14. 14.
    S. Lawrence, C. Lee Giles, A. Chung Tsoi, and A. Back, “Face recognition: A convolutional neural network approach,” IEEE Transactions on Neural Networks, Special Issue on Neural Networks and Pattern Recognition, 1997.Google Scholar
  15. 15.
    R. Gonzalez and R. Woods, Digital Image Processing, Addison-Wesley: USA, 1993.Google Scholar
  16. 16.
    G. de Trémiolles, P. Tannhof, B. Plougonven, C. Demarigny, and K. Madani, “Visual probe mark inspection using hardware implementation of artificial neural networks,” in VLSI Production, Lecture Notes in Computer Science, edited by Springer Verlag, Jun 1997.Google Scholar
  17. 17.
    S.P. Luttrel, “Optimal response functions in a network of discretely firing neurons,” in 5th IEE Conference on Artificial Neural Networks, Cambridge, 1997.Google Scholar

Copyright information

© Kluwer Academic Publishers 2003

Authors and Affiliations

  • Kurosh Madani
    • 1
  • Ghislain de Trémiolles
    • 2
  • Pascal Tannhof
    • 2
  1. 1.Intelligence in Instrumentation and Systems—I2S, SENART Institute of TechnologyUniversity PARIS XIILIEUSAINTFrance
  2. 2.IBM France, Laboratoire d'Etude et de DeveloppementCorbeil Essonnes CedexFrance

Personalised recommendations