Variational Bayesian blind image deconvolution based on a sparse kernel model for the point spread function

In this paper we propose a variational Bayesian algorithm for the blind image deconvolution problem. The unknown point spread function (PSF) is modeled as a sparse linear combination of kernel basis functions. This model offers an effective mechanism to estimate for the first time both the support and the shape of the PSF. Numerical experiments demonstrate the effectiveness of the proposed methodology.

[1]  Nikolas P. Galatsanos,et al.  Non stationary Bayesian image restoration , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[2]  Aggelos K. Katsaggelos,et al.  Approximations of posterior distributions in blind deconvolution using variational methods , 2005, IEEE International Conference on Image Processing 2005.

[3]  Nikolas P. Galatsanos,et al.  A variational approach for Bayesian blind image deconvolution , 2004, IEEE Transactions on Signal Processing.

[4]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[5]  Michael E. Tipping,et al.  A Variational Approach to Robust Regression , 2001, ICANN.

[6]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine Learning.