Modeling non Gaussian and non stationary signals and images has always beenone of the most important part of signal and image processing methods. In thispaper, first we propose a few new models, all based on using hidden variablesfor modeling either stationary but non Gaussian or Gaussian but non stationaryor non Gaussian and non stationary signals and images. Then, we will see how touse these models in independent component analysis (ICA) or blind sourceseparation (BSS). The computational aspects of the Bayesian estimationframework associated with these prior models are also discussed.
展开▼
