USING LOGARITHMIC OPINION POOLING TECHNIQUES IN BAYESIAN BLIND MULTI-CHANNEL RESTORATION

Bruno Amizic, Aggelos K. Katsaggelos, Rafael Molina

Abstract

In this paper we examine the use of logarithmic opinion pooling techniques to combine two observations models that are normally used in multi-channel image restoration techniques. The combined observation model is used together with simultaneous autoregression prior models for the image and blurs to define the joint distribution of image, blurs and observations. Assuming that all the unknown parameters are previously estimated we use variational techniques to approximate the posterior distribution of the real underlying image and the unknown blurs. We will examine the use of two approximations of the posterior distribution. Experimental results are used to validate the proposed approach.

References

  1. Bishop, T., Babacan, D., Amizic, B., Katsaggelos, A. K., Chan, T., and Molina, R. (2007). Blind image deconvolution: problem formulation and existing approaches. In Campisi, P. and Egiazarian, K., editors, Blind image deconvolution: Theory and Applications, chapter 1, pages 1-42. CRC.
  2. Galatsanos, N. P., Mesarovic, V. Z., Molina, R., Katsaggelos, A. K., and Mateos, J. (2002). Hyperparameter estimation in image restoration problems with partiallyknown blurs. Optical Eng., 41(8):1845-1854.
  3. Gastaud, M., Ladjal, S., and Matre, H. (2007). Blind filter identification and image superresolution using subspace methods. In European Signal Processing Conference. Poznan (Poland).
  4. Genest, C. and Zidek, J. V. (1986). Combining probability distributions: A critique and an annotated bibliography. Statistical Science, 1:114148.
  5. Katsaggelos, A., Molina, R., and Mateos, J. (2007). Super resolution of images and video. Synthesis Lectures on Image, Video, and Multimedia Processing. Morgan and Claypool.
  6. Kullback, S. (1959). Information Theory and Statistics. New York, Dover Publications.
  7. Kullback, S. and Leibler, R. A. (1951). On information and sufficiency. Annals of Mathematical Statistics, 22:79- 86.
  8. Mateos, J., Katsaggelos, A., and Molina, R. (2000). A Bayesian approach to estimate and transmit regularization parameters for reducing blocking artifacts. 9(7):1200-1215.
  9. Molina, R., Katsaggelos, A. K., and Mateos, J. (1999). Bayesian and regularization methods for hyperparameter estimation in image restoration. 8(2):231-246.
  10. Molina, R., Mateos, J., and Katsaggelos, A. (2006). Blind deconvolution using a variational approach to parameter, image, and blur estimation. IEEE Trans. on Image Processing, 15(12):3715-3727.
  11. Ripley, B. D. (1981). Spatial Statistics, pages 88-90. John Wiley.
  12. Sroubek, F., Cristóbal, G., and Flusser, J. (2007). A unified approach to superresolution and multichannel blind deconvolution. IEEE Transactions on Image Processing, 9:2322-2332.
Download


Paper Citation


in Harvard Style

Amizic B., K. Katsaggelos A. and Molina R. (2008). USING LOGARITHMIC OPINION POOLING TECHNIQUES IN BAYESIAN BLIND MULTI-CHANNEL RESTORATION . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: BAIPCV, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 565-570. DOI: 10.5220/0001091405650570


in Bibtex Style

@conference{baipcv08,
author={Bruno Amizic and Aggelos K. Katsaggelos and Rafael Molina},
title={USING LOGARITHMIC OPINION POOLING TECHNIQUES IN BAYESIAN BLIND MULTI-CHANNEL RESTORATION},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: BAIPCV, (VISIGRAPP 2008)},
year={2008},
pages={565-570},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001091405650570},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: BAIPCV, (VISIGRAPP 2008)
TI - USING LOGARITHMIC OPINION POOLING TECHNIQUES IN BAYESIAN BLIND MULTI-CHANNEL RESTORATION
SN - 978-989-8111-21-0
AU - Amizic B.
AU - K. Katsaggelos A.
AU - Molina R.
PY - 2008
SP - 565
EP - 570
DO - 10.5220/0001091405650570