1 August 2002 Hyperparameter estimation in image restoration problems with partially-known blurs
Author Affiliations +
This work is motivated by the observation that it is not possible to reliably estimate simultaneously all the necessary hyperparameters in an image restoration problem when the point-spread function is assumed to be the sum of a known deterministic and an unknown random component. To solve this problem we propose to use gamma hyperpriors for the unknown hyperparameters. Two iterative algorithms that simultaneously restore the image and estimate the hyperparameters are derived, based on the application of evidence analysis within the hierarchical Bayesian framework. Numerical experiments are presented that show the benefits of introducing hyperpriors for this problem.
© (2002) Society of Photo-Optical Instrumentation Engineers (SPIE)
Nikolas P. Galatsanos, Nikolas P. Galatsanos, Vladimir Z. Mesarovic, Vladimir Z. Mesarovic, Rafael Molina, Rafael Molina, Aggelos K. Katsaggelos, Aggelos K. Katsaggelos, Javier Mateos, Javier Mateos, } "Hyperparameter estimation in image restoration problems with partially-known blurs," Optical Engineering 41(8), (1 August 2002). https://doi.org/10.1117/1.1487850 . Submission:

Back to Top