Bayesian Image Segmentation Using MRF’s Combined with Hierarchical Prior Models
The problem of image segmentation can be formulated in the framework of Bayesian statistics. We use a Markov random field as the prior model of the spacial relationship between image pixels, and approximate an observed image by a Gaussian mixture model. In this paper, we introduce into the statistical model a hierarchical prior structure from which model parameters are regarded as drawn. This would give an efficient Gibbs sampler for exploring the joint posterior distribution of all parameters given an observed image and could make the estimation more robust.
KeywordsMixture Model Posterior Distribution Markov Chain Monte Carlo Image Segmentation Gibbs Sampler
- 1.Barker, S.A.: Image Segmentation using Markov Random Field Models, PhD thesis, University of Cambridge (1998)Google Scholar
- 6.Kato, Z.: Bayesian Color Image Segmentation Using Reversible Jump Markov Chain Monte Carlo, Research Report PNA-R9902, CWI (1999)Google Scholar
- 8.Stephens, M.: Bayesian Methods for Mixture of Normal Distributions, PhD thesis, University of Oxford (1997)Google Scholar