Binomial filters

  • Matthew Aubury
  • Wayne Luk
Article

Abstract

Binomial filters are simple and efficient structures based on the binomial coefficients for implementing Gaussian filtering. They do not require multipliers and can therefore be implemented efficiently in programmable hardware. There are many possible variations of the basic binomial filter structure, and they provide a wide range of space-time trade-offs; a number of these designs have been captured in a parametrised form and their features are compared. This technique can be used for multi-dimensional filtering, provided that the filter is separable. The numerical performance of binomial filters, and their implementation using field-programmable devices for an image processing application, are also discussed.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    S.Y. Kung,VLSI Array Processors, Prentice Hall, 1988.Google Scholar
  2. 2.
    W. Luk, “Systematic pipelining of processor arrays,” G.M. Megson (ed.),Transformational Approaches to Systolic Design, Chapman and Hall Parallel and Distributed Computing Series, 1994, pp. 77–98.Google Scholar
  3. 3.
    W. Luk, “Systematic eerialisation of array-based architectures,”Integration, Vol. 14, No. 3, pp 333–360, 1993.MATHGoogle Scholar
  4. 4.
    H.K. Nishihara,Real-Time Implementation of a Sign-Correlation Algorithm for Image-Matching, Technical Report No. TR-90-02, Teleos Research, 1990.Google Scholar
  5. 5.
    W.M. Wells, “Efficient synthesis of Gaussian filters by cascaded uniform filters,”IEEE Trans. PAMI, Vol. 8, pp. 234–239, 1992.Google Scholar
  6. 6.
    J. Canny,Finding Edges and Lines in Images, M.Sc. Thesis, Massachusetts Institute of Technology, 1983.Google Scholar
  7. 7.
    D. David, T. Court, J.L. Jacquot, and A. Pirson, “INP 20: An image neighborhood processor for large kernels,”Proc. IAPR Workshop on Computer Vision: Special Hardware and Industrial Applications, University of Tokyo, pp. 241–244, 1988.Google Scholar
  8. 8.
    A. Chehikian and J.L. Crowley, “Fast computation of optimal semi-octave pyramids,” 7th S.C.I.A., Aalborg, August 1991.Google Scholar
  9. 9.
    R.N. Bracewell,The Fourier Transform and its Applications, McGraw-Hill, 1986.Google Scholar
  10. 10.
    S. Guo, W. Luk, and P. Probert, “Developing parallel architectures for range and image sensors,”Proc. IEEE International Conference on Robotics and Automation, pp. 2205–2210, 1994.Google Scholar
  11. 11.
    Xilinx Inc.,The Programmable Logic Data Book, 1994.Google Scholar
  12. 12.
    S. Guo and W. Luk, “Compiling Ruby into FPGAs,” W. Luk and W.R. Moore (eds.),Field-Programmable Logic and Applications, Lecture Notes in Computer Science 975, Springer Verlag, pp. 188–197, 1995.Google Scholar
  13. 13.
    G. Jones and M. Sheeran, “Circuit deign in Ruby,” J. Staunstrup (ed.),Formal Methods for VLSI Design, North-Holland, pp. 13–70, 1990.Google Scholar
  14. 14.
    W. Luk and I. Page, “Parameterising designs for FPGAs,” W.R. Moore and W. Luk (eds.),FPGAs, Abingdon EE & CS Books, pp. 284–295, 1991.Google Scholar
  15. 15.
    A. Lawrence, A. Kay, W. Luk, T. Nomura, and I. Page, “Using reconfigurable hardware to speed up product development and performance,” W. Luk and W.R. Moore (eds.),Field-Programmable Logic and Applications, Lecture Notes in Computer Science 975, Springer Verlag, pp. 111–118, 1995.Google Scholar
  16. 16.
    Algotronix Ltd,CHS2x4 Custom Computer User Manual, 1992.Google Scholar
  17. 17.
    W. Luk, T. Wu, and I. Page, “Hardware-software codesign of multidimensional algorithms,” D.A. Buell and K.L. Pocek (eds.),Proc. IEEE Workshop on FPGAs for Custom Computing Machines, IEEE Computer Society Press, pp. 82–90, 1994.Google Scholar
  18. 18.
    W. Luk and T. Wu, “Towards a declarative framework for hardware-software codesign,”Proc. Third International Workshop on Hardware/Software Codesign, IEEE Computer Society Press, pp. 181–188, 1994.Google Scholar
  19. 19.
    M.C. Mozer,Neural Network Architectures for Temporal Sequence Processing, Predicting the Future and Understanding the Past, Addison Wesley, 1993.Google Scholar
  20. 20.
    H.K. Nishihara,System for Expedited Computation of Laplacian and Gaussian Filters and Correlation of Their Outputs for Image Processing, United States Patent 5119444, June 1992.Google Scholar

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • Matthew Aubury
    • 1
  • Wayne Luk
    • 2
  1. 1.Programming Research GroupOxford University Computing LaboratoryOxfordEngland
  2. 2.Department of ComputingImperial CollegeLondonEngland

Personalised recommendations