论文信息 - Weighted Median Predictive Techniques for Coe cient Estimation in NonGaussian Markov Random Fields

Weighted Median Predictive Techniques for Coe cient Estimation in NonGaussian Markov Random Fields

NonGaussian Markov image models are e ective in the preservation of edge detail in Bayesian formulations of restoration and reconstruction problems. Included in these models are coe cients quantifying the statistical links among pixels in local cliques, which are typically assumed to have an inverse dependence on distance among the corresponding neighboring pixels. Estimation of these coe cients is a nontrivial task for NonGaussian models. We present results for coe cient estimation for a model which is particularly e ective for edge preservation and noise suppression, using a predictive technique analogous to estimation of the weights of optimal weighted median lters.

Sean Borman | Ken Sauer

[1] Ken D. Sauer,et al. A generalized Gaussian image model for edge-preserving MAP estimation , 1993, IEEE Trans. Image Process..

[2] Jeffrey A. Fessler. Mean and variance of implicitly defined biased estimators (such as penalized maximum likelihood): applications to tomography , 1996, IEEE Trans. Image Process..

[3] Moncef Gabbouj,et al. Minimum Mean Absolute Error Stack Filtering with Structural Constraints and Goals , 1990 .

[4] Moncef Gabbouj,et al. 2-D Optimal Weighted Median Filters , 1992 .

[5] Donald Geman,et al. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[6] Donald Geman,et al. Gibbs distributions and the bayesian restoration of images , 1984 .

[7] Ken D. Sauer,et al. Maximum likelihood scale estimation for a class of Markov random fields , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.