Abstract
The framework is presented of Bayesian image restoration for multi-valued images based on the Q-state Potts model. Hyperparameters in the probabilistic model are determined so as to maximize the marginal likelihood. A practical algorithm is described for multi-valued image restoration based on loopy belief propagation. We conclude that the maximization of marginal likelihood can provide good results even if the a priori probabilistic model exhibits first-order phase transition.
Original language | English |
---|---|
Pages (from-to) | 288-291 |
Number of pages | 4 |
Journal | Progress of Theoretical Physics Supplement |
Volume | 157 |
DOIs | |
Publication status | Published - 2005 |
ASJC Scopus subject areas
- Physics and Astronomy (miscellaneous)