Scale hyperparameter estimation for GGMRF prior models with application to SPECT images

A. Lopez1, R. Molina2, A.K. Katsaggelos3
1Departamento de Lenguajes y Sistemas Informaticos, Universidad de Granada, Granada, Spain
2Departamento de Ciencias de la Cornputacion e I. A., Universidad de Granada, Granada, Spain
3Department of Electrical and Computer Engineering, Northwestern University, Evaston, Illinois

Tóm tắt

In this work we develop a Bayesian reconstruction method for SPECT (single photon emission computed tomography) images, using as prior GGMRF (generalized Gaussian Markov random fields) distributions and estimating the scale hyperparameter following the evidence analysis. Preconditioning methods are used to estimate this hyperparameter and the approximations used are compared on synthetic images.

Từ khóa

#Image reconstruction #Degradation #Bayesian methods #Application software #Image analysis #Distributed computing #Optical computing #Reconstruction algorithms #Single photon emission computed tomography #Markov random fields

Tài liệu tham khảo

10.1109/83.535846 10.1109/78.157228 lopez, 1999, $\Sigma{\rm Hy}-$ perparameter Estimation for Emission Computed Tomography Datal, Proc of the Int Conf on Image Processing ICIP-99, 2, 667 10.1109/83.760336 10.1109/23.340655 bouman, 1998, $\Sigma{\rm Parame}-$ ter Estimation for Markov Random Fields with Applications to Bayesian Tomography, IEEE Trans on Image Processing, 7, 445 10.1109/42.222670 10.1080/01621459.1997.10473602 10.1109/83.236536