gibbsPotts

Fit a hidden Potts model to the observed data, using a fixed value of beta.

Various algorithms for segmentation of 2D and 3D images, such
as computed tomography and satellite remote sensing. This package implements
Bayesian image analysis using the hidden Potts model with external field
prior of Moores et al. (2015) <doi:10.1016/j.csda.2014.12.001>.
Latent labels are sampled using chequerboard updating or Swendsen-Wang.
Algorithms for the smoothing parameter include pseudolikelihood, path sampling,
the exchange algorithm, approximate Bayesian computation (ABC-MCMC and ABC-SMC),
and the parametric functional approximate Bayesian (PFAB) algorithm. Refer to
Moores, Pettitt & Mengersen (2020) <doi:10.1007/978-3-030-42553-1_6> for an overview
and also to <doi:10.1007/s11222-014-9525-6> and <doi:10.1214/18-BA1130> for
further details of specific algorithms.

Matt Moores

bayesImageS

Bayesian Methods for Image Segmentation using a Potts Model

Dai Feng

Kerrie Mengersen

gibbsPotts function

<dl><dt>y</dt>
<dd>A vector of observed pixel data.</dd>
<dt>labels</dt>
<dd>A matrix of pixel labels.</dd>
<dt>beta</dt>
<dd>The inverse temperature parameter of the Potts model.</dd>
<dt>mu</dt>
<dd>A vector of means for the mixture components.</dd>
<dt>sd</dt>
<dd>A vector of standard deviations for the mixture components.</dd>
<dt>neighbors</dt>
<dd>A matrix of all neighbors in the lattice, one row per pixel.</dd>
<dt>blocks</dt>
<dd>A list of pixel indices, dividing the lattice into independent blocks.</dd>
<dt>priors</dt>
<dd>A list of priors for the parameters of the model.</dd>
<dt>niter</dt>
<dd>The number of iterations of the algorithm to perform.</dd></dl>

Arguments

Fit a hidden Potts model to the observed data, using a fixed value of beta. — gibbsPotts

<dl>

<dt>y</dt>
<dd>A vector of observed pixel data.</dd>


<dt>labels</dt>
<dd>A matrix of pixel labels.</dd>


<dt>beta</dt>
<dd>The inverse temperature parameter of the Potts model.</dd>


<dt>mu</dt>
<dd>A vector of means for the mixture components.</dd>


<dt>sd</dt>
<dd>A vector of standard deviations for the mixture components.</dd>


<dt>neighbors</dt>
<dd>A matrix of all neighbors in the lattice, one row per pixel.</dd>


<dt>blocks</dt>
<dd>A list of pixel indices, dividing the lattice into independent blocks.</dd>


<dt>priors</dt>
<dd>A list of priors for the parameters of the model.</dd>


<dt>niter</dt>
<dd>The number of iterations of the algorithm to perform.</dd>

</dl>

gibbsPotts: Fit a hidden Potts model to the observed data, using a fixed value of beta.

Description

Usage

Value

Arguments