Image Modeling

  • Robert King
  • Majid Ahmadi
  • Raouf Gorgui-Naguib
  • Alan Kwabwe
  • Mahmood Azimi-Sadjadi


In the preceding chapters, the design and analysis of recursive and nonrecur-sive one-dimensional (1-D) and two-dimensional (2-D) digital filters have been discussed for the case of deterministic input signals. However, in situations such as satellite and radar imaging, knowledge of the original image is not deterministically available. Each pixel is considered as a random variable and the image is thought of as a sample of an ensemble of images. For simplicity in modeling, the image is assumed to have a Gaussian distribution which can be specified uniquely by its first- and second-order moments (mean and covariances). To perform the estimation and filtering process, the image should be represented by an appropriate statistical model.


Causal Model Image Restoration Colored Noise ARMA Model Spectral Density Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    A. K. Jain and J. R. Jain, Partial difference equations and finite difference methods in image processing—Part 2: image restoration, IEEE Trans. Autom. Control AC-23, 817–833 (1978).CrossRefGoogle Scholar
  2. 2.
    J. W. Woods and C. H. Radewan, Kaiman filtering in two dimensions, IEEE Trans. Inf. Theory IT-23, 473–482 (1977).MathSciNetCrossRefGoogle Scholar
  3. 3.
    B. R. Suresh and B. A. Shenoi, New results in two-dimensional Kaiman filtering with applications to image restoration, IEEE Trans. Circuits Syst. CAS-28, 307–319 (1981).CrossRefGoogle Scholar
  4. 4.
    M. R. Azimi-Sadjadi and P. W. Wong, Two-dimensional block Kaiman filtering for image restoration, IEEE Trans. Acoust., Speech, Signal Process ASSP-35, 1736–1749 (1987).CrossRefGoogle Scholar
  5. 5.
    E. J. Delp, R. L. Kashyap, and O. R. Mitchell, Image data compression using autoregressive time series models, Pattern Recognition 11, 313–323 (1979).CrossRefGoogle Scholar
  6. 6.
    R. Chellappa and R. L. Kashyap, Texture synthesis using 2-D noncausal autoregressive models, IEEE Trans. Acoust., Speech, Signal Process ASSP-33, 194–202 (1985).CrossRefGoogle Scholar
  7. 7.
    S. Lawrence Marple, Jr., Digital Spectral Analysis with Applications, Prentice-Hall, Engle-wood Cliffs, NJ (1987).Google Scholar
  8. 8.
    R. Kumar, A fast algorithm for solving a Toeplitz system of equations, IEEE Trans. Acoust., Speech, Signal Process ASSP-33, 254–267 (1985).CrossRefGoogle Scholar
  9. 9.
    P. J. Brockwell and R. A. Davis, Time Series Theory and Methods, Springer-Verlag, Berlin (1987).zbMATHGoogle Scholar
  10. 10.
    A. K. Jain, Advances in mathematical models for image processing, Proc. IEEE 69, 502–528 (1981).CrossRefGoogle Scholar
  11. 11.
    S. Ranganath and A. K. Jain, Two-dimensional linear prediction models—Part 1: Spectral factorization and realization, IEEE Trans. Acoust., Speech, Signal Process ASSP-33, 280–299 (1985).CrossRefGoogle Scholar
  12. 12.
    R. L. Kashyap, Characterization and estimation of two-dimensional ARMA models, IEEE Trans. Inf. Theory IT-30, 736–745 (1984).MathSciNetCrossRefGoogle Scholar
  13. 13.
    A. K. Jain, A semicausal model for recursive filtering of two-dimensional images, IEEE Trans. Comput. C-26, 343–350 (1977).CrossRefGoogle Scholar
  14. 14.
    G. C. Verghese, B. C. Levy, and T. Kailath, A generalized state-space for singular systems, IEEE Trans. Autom. Control AC-26, 811–831 (1981).MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1989

Authors and Affiliations

  • Robert King
    • 1
  • Majid Ahmadi
    • 2
  • Raouf Gorgui-Naguib
    • 3
  • Alan Kwabwe
    • 4
  • Mahmood Azimi-Sadjadi
    • 5
  1. 1.Imperial CollegeLondonEngland
  2. 2.University of WindsorWindsorCanada
  3. 3.University of Newcastle upon TyneNewcastle upon TyneEngland
  4. 4.Imperial College and Bankers Trust CompanyLondonEngland
  5. 5.Colorado State UniversityFort CollinsUSA

Personalised recommendations