This Article 
 Bibliographic References 
 Add to: 
On the Hierarchical Bayesian Approach to Image Restoration: Applications to Astronomical Images
November 1994 (vol. 16 no. 11)
pp. 1122-1128

In an image restoration problem one usually has two different kinds of information. In the first stage, one has knowledge about the structural form of the noise and local characteristics of the restoration. These noise and image models normally depend on unknown hyperparameters. The hierarchical Bayesian approach adds a second stage by putting a hyperprior on the hyperparameters, where information about those hyperparameters is included. In this work the author applies the hierarchical Bayesian approach to image restoration problems and compares it with other approaches in handling the estimation of the hyperparameters.

[1] H. M. Adorf, "HST image restoration-status and prospects," inData Analysis in Astronomy, vol IV, V. Di Gesù, L. Scarsi, R. Buccheri, P. Crane, M. C. Maccarone, and H. U. Zimmermann, eds. New York: Plenum Press. pp. 83-96, 1992.
[2] J. O. Berger,Statistical Decision Theory and Bayesian Analysis. New York: Springer Verlag, 1985, chaps. 3 and 4.
[3] A. Blake and A. Zisserman,Visual Reconstruction. Cambridge, MA: MIT Press, 1987.
[4] W.L. Buntine and A. Weigend, "Bayesian back-propagation,"Complex Systems, vol. 5, pp. 603-643, 1991.
[5] A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data,"J. Royal Statist. Soc. B, vol. 39, pp. 1-38, 1972.
[6] D. Geman, "Random fields and inverse problems in imaging," inÉcole d'Étéde Probabilités de Saint-Flour XVIII-1988, P. L Hennequin, Ed. New York: Springer-Verlag, pp. 172-175, 1990.
[7] S. F. Gull, "Developments in maximum entropy data analysis," inMaximum Entropy and Bayesian Methods, J. Skilling, Ed. Norwell, MA: Kluwer Academic Press, pp. 53-71, 1989.
[8] S. F. Gull and J. Skilling,MEMSYS 5 Users's Manual. Maximum Entropy Consultants Ltd., 1991.
[9] M. G. Kang and A. K. Katsaggelos, "Simultaneous iterative image restoration and evaluation of the regularization parameter,"IEEE Trans. Signal Processing, vol. 40, pp. 2329-2344, 1992.
[10] A. K. Katsaggelos and M. G. Kang, "Iterative evaluation of the regularization parameter in regularized image restoration,"J. Visual Communication and Image Representation, vol. 3, pp 446-455, 1992.
[11] J. Llacer and J. Núñez, "Iterative maximum likelihood estimator and Bayesian algorithms for image reconstruction in astronomy," inThe Restoration of HST Images and Spectra, R. L. White and R. J. Allen, Eds. Baltimore, MD: STScI, pp. 62-70, 1990.
[12] L. B. Lucy, "An iterative technique for the rectification of observed distributions,"Astron. J., vol. 79, 745-754, 1974.
[13] D. J. C. MacKay, "A practical Bayesian framework for backprop networks,"Neural Computation, vol. 4, pp. 448-472, 1992.
[14] D. J. C. MacKay, "Bayesian interpolation,"Neural Computation, vol. 4, pp. 415-447, 1992.
[15] R. Molina, N. Pérez de la Blanca, and B. D. Ripley, "Statistical restoration of astronomical images," inData Analysis in Astronomy, vol. III, V. Di Gesu, L. Scarsi, P. Crane, J. H. Friedman, S. Levialdi, and M. C. Maccarone, Eds. New York: Plenum Press, pp. 75-82, 1992.
[16] R. Molina and B. D. Ripley, "Using spatial models as priors in astronomical images analysis,"J. Appl. Statist., vol. 16, pp. 193-206, 1989.
[17] R. Molina, A. del Olmo, J. Perea, and B. D. Ripley, "Bayesian deconvolution in optical astronomy,"Astrom. J., vol. 103, pp. 666-675, 1992.
[18] R. Molina, B. D. Ripley, A. Molina, F. Moreno, and J. L. Ortiz, "Bayesian deconvolution with prior knowledge of object location. applications to ground-based planetary images,"Astrom. J., vol. 104, pp. 1662-1668, 1992.
[19] R. Molina and A. K. Katsaggelos, "On the iterative evaluation of the regularization parameter and the hierarchical Bayesian approach to image restoration," submitted to the Conference on Visual Communications and Image Processing '94, 1994.
[20] L. Reginald and J. Biemond,Iterative Identification and Restoration of Images. Norwell, MA: Kluwer Academic Press, pp. 3 and 124-129, 1991.
[21] W. H. Richardson, "Bayesian-based iterative methods of image restoration,"J. Opt. Soc. Am., vol. 62, pp. 52-55, 1972.
[22] B. D. Ripley,Spatial Statistics. New York: John Wiley, pp. 88-90, 1981.
[23] B. D. R. Ripley,Statistical Inference for Spatial Processes. London: Cambridge University Press, 1988.
[24] A. M. Thompson, J. C. Brown, J. W. Kay, and D. M. Titterington, "A study of methods of choosing the smoothing parameters in image restoration by regularization,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, pp. 326-339, 1991.
[25] Y. Vardi and D. Lee, "From image debluring to optimal investments: Maximum likelihood solutions for positive linear inverse problems (with discussion),"J. R. Statist. Soc. B, vol. 55, pp. 569-612, 1993.
[26] N. Weir, "Recent developments in maximum entropy based image restoration,"ST-ECF Newsletter, vol. 16, pp. 8-11, 1991.
[27] R. L. White and R. J. Allen, eds,Proc. Workshop The Restoration of HST Images and Spectra, Space Telescope Science Institute, Baltimore, 21-22 August, 1990.

Index Terms:
image restoration; Bayes methods; maximum likelihood estimation; astronomy; hierarchical Bayesian approach; image restoration; astronomical images; noise; local characteristics; image models; hyperprior; hyperparameters estimation
R. Molina, "On the Hierarchical Bayesian Approach to Image Restoration: Applications to Astronomical Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 11, pp. 1122-1128, Nov. 1994, doi:10.1109/34.334393
Usage of this product signifies your acceptance of the Terms of Use.