Abstract

This paper presents a derivation of a fast recursive filter for colour image restoration if degradation obeys a linear degradation model with the unknown possibly non-homogeneous point-spread function. Pixels in the vicinity of steep discontinuities are left unrestored to minimize restoration blurring effect. The degraded image is assumed to follow a causal simultaneous multidimensional regressive model and the point-spread function is estimated using the local least-square estimate.

Keywords

Image Restoration Markov Chain Monte Carlo Method Degradation Model Restoration Method Corrupted Image 
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.

References

  1. 1.
    Andrews, H. C., Hunt, B.: Digital Image Restoration. Prentice-Hall, Englewood Cliffs (1977)Google Scholar
  2. 2.
    Chalmond, B.: Image restoration using an estimated markov model. Signal Processing 15 (1988) 115–129CrossRefGoogle Scholar
  3. 3.
    Chellappa, R., Kashyap, R.: Digital image restoration using spatial interaction models. IEEE Trans. Acoustics, Speech and Sig. Proc. 30 (1982) 284–295Google Scholar
  4. 4.
    Deguchi, K., Morishita, I.: Two-dimensional auto-regressive model for the representation of random image fields. In: Proc.ICPR Conf., IEEE, Munich (1982) 90–93Google Scholar
  5. 5.
    Fischl, B., Schwartz, E.: Learning an integral equation approximation to nonlinear anisotropic diffusion in image processing. IEEE Trans. Pattern Anal. Mach. Int. 19 (1997) 342–352CrossRefGoogle Scholar
  6. 6.
    Geman, D.: Random fields and inverse problems in imaging. Springer, Berlin, 1990Google Scholar
  7. 7.
    Geman, S., Geman, D.: Stochastic relaxation, gibbs distributions and bayesian restoration of images. IEEE Trans. Pattern Anal. Mach. Int. 6 (1984) 721–741MATHCrossRefGoogle Scholar
  8. 8.
    Haindl, M.: Recursive model-based image restoration. In: Proc. of the 13th ICPR Conf. vol. III, IEEE Press, Barcelona (2000) 346–349Google Scholar
  9. 9.
    Haindl, M.: Recursive square-root filters. In: Proc. of the 13th ICPR Conf. vol. II, IEEE Press, Barcelona (2000) 1018–1021Google Scholar
  10. 10.
    Haindl, M., Šimberová, S.: A high-resolution radiospectrograph image reconstruction method. Astronomy and Astrophysics, Suppl.Ser. 115 (1996) 189–193Google Scholar
  11. 11.
    Haindl, M., Šimberová, S.: A scratch removal method. Kybernetika 34 (1998) 423–428Google Scholar
  12. 12.
    Hunt, B.: The application of constraint least square estimation to image restoration by digital computer. IEEE Trans. Computers 22 (1973) 805–812CrossRefGoogle Scholar
  13. 13.
    Jeffs, B., Pun, W.: Simple shape parameter estimation from blurred observations for a generalized Gaussian mrf image prior used in map restoration. In: Proc. IEEE CVPR Conf., IEEE, San Francisco (1996) 465–468Google Scholar
  14. 14.
    Lagendijk, R., Biemond, J., Boekee, D.: Identification and restoration of noisy blurred images using the expectation-maximization algorithm. IEEE Trans. on Acoust., Speech, Signal Processing 38 (1990) 1180–1191MATHCrossRefGoogle Scholar
  15. 15.
    Marroquin, J., Poggio, T.: Probabilistic solution of ill-posed problems in computational vision. J. Am. Stat. Assoc. 82 (1987) 76–89MATHCrossRefGoogle Scholar
  16. 16.
    Nitzberg, M., T. Shiota, T.: Nonlinear image filtering with edge and corner enhancement. IEEE Trans. Pattern Anal. Mach. Int. 16 (1992) 826–833CrossRefGoogle Scholar
  17. 17.
    Perona, P.: Deformable kernels for early vision. IEEE Trans. Pattern Anal. Mach. Int. 17 (1995) 488–489CrossRefGoogle Scholar
  18. 18.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Int. 12 (1990) 629–639CrossRefGoogle Scholar
  19. 19.
    Reeves, S., Mersereau, R.: Identification by the method of generalized cross-validation. IEEE Trans. Im. Processing 1 (1992) 301–311CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Michal Haindl
    • 1
  1. 1.Academy of SciencesInstitute of Information Theory and AutomationPragueCzech Republic

Personalised recommendations