bayesImagesS: Bayesian methods for image segmentation using a hidden Potts model

R package, bayesimageS, implements Bayesian image analysis using the hidden Potts model with external field prior. Ltent labels are sampled using chequerboard updating or Swendsen-Wang. Algorithms for the smoothing parameter include pseudolikelihood, path sampling, the exchange algorithm and approximate Bayesian computation. This R package was written during a QUT based PhD, which was a collaborative project between QUT and the Radiation Oncology Mater Centre, Queensland Health titled, Bayesian computational methods for spatial analysis of images. It is an R source package (.tar.gz) containing.R and .cpp (R and C++) source code.

R包bayesimageS实现了基于带外场先验的隐Potts模型（hidden Potts model）的贝叶斯图像分析。其潜在标签通过棋盘格更新法或斯温森-王算法（Swendsen-Wang）进行采样。平滑参数的求解算法包括伪似然法、路径抽样法、交换算法以及近似贝叶斯计算（approximate Bayesian computation）。该R包是在昆士兰科技大学（QUT）的博士研究期间编写完成，该项研究为昆士兰科技大学与昆士兰州卫生厅马特放射肿瘤中心（Radiation Oncology Mater Centre, Queensland Health）合作开展的题为《面向图像空间分析的贝叶斯计算方法》的项目。本软件为.tar.gz格式的R源码包，包含R语言（.R）与C++语言（.cpp）的源代码文件。