Exact distribution of edge-preserving MAP estimators for linear signal models with Gaussian measurement noise
Authors:
- J.A. FesslerJFJ.A. Fessler
- H. ErdoganHEH. Erdogan
- Wei Biao WuWWWei Biao Wu
- 1 June 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 9 (6) , 1049-1055
Abstract
We derive the exact statistical distribution of maximum a posteriori (MAP) estimators having edge-preserving nonGaussian priors. Such estimators have been widely advocated for image restoration and reconstruction problems. Previous investigations of these image recovery methods have been primarily empirical; the distribution we derive enables theoretical analysis. The signal model is linear with Gaussian measurement noise. We assume that the energy function of the prior distribution is chosen to ensure a unimodal posterior distribution (for which convexity of the energy function is sufficient), and that the energy function satisfies a uniform Lipschitz regularity condition. The regularity conditions are sufficiently general to encompass popular priors such as the generalized Gaussian Markov random field prior and the Huber prior, even though those priors are not everywhere twice continuously differentiable.Keywords
This publication has 12 references indexed in Scilit:
- Inversion of large-support ill-posed linear operators using a piecewise Gaussian MRFIEEE Transactions on Image Processing, 1998
- Globally convergent edge-preserving regularized reconstruction: an application to limited-angle tomographyIEEE Transactions on Image Processing, 1998
- Deterministic edge-preserving regularization in computed imagingIEEE Transactions on Image Processing, 1997
- Mean and variance of implicitly defined biased estimators (such as penalized maximum likelihood): applications to tomographyIEEE Transactions on Image Processing, 1996
- A stochastic algorithm for parametric and non-parametric estimation in the case of incomplete dataSignal Processing, 1995
- Edge-preserving tomographic reconstruction from gaussian data using a gibbs prior and a generalized expectation-maximization algorithmInternational Journal of Imaging Systems and Technology, 1994
- A Model for Segmentation and Analysis of Noisy ImagesJournal of the American Statistical Association, 1994
- A generalized Gaussian image model for edge-preserving MAP estimationIEEE Transactions on Image Processing, 1993
- Convergence of EM image reconstruction algorithms with Gibbs smoothingIEEE Transactions on Medical Imaging, 1990
- On a formula for the distribution of the maximum likelihood estimatorBiometrika, 1983