Restoration of noisy regions modeled by noncausal Markov randomfields of unknown parameters

摘要

, is modeledas a noncausal Markov random field (MRF), namely, either a multilevellogistic (MLL) or a Gaussian MRF, and is corrupted by additiveindependently identically distributed (i.i.d.) Gaussian noise. Theapplication is a restoration/segmentation of regions of interest in animage obtained from histologies of brain sections, which suggests an MLLmodeling since the regions are spatially smooth. The presented algorithmmaximizes the joint likelihood of the observations,