Parameters for image inv_model.gaussian_prior_likelihood.img_mean -> image mean inv_model.gaussian_prior_likelihood.R_prior -> L*L' = inv(image covariance) inv_model.gaussian_prior_likelihood.img_exp -> ( default = 2) Parameters for data inv_model.gaussian_prior_likelihood.Noise -> L*L' = inv(Noise covariance) inv_model.gaussian_prior_likelihood.data_exp -> ( default = 2) Function to be used with inv_solve_mcmc
0001 function likelihood= prior_gaussian_likelihood( inv_model, x, y, J ) 0002 % Parameters for image 0003 % inv_model.gaussian_prior_likelihood.img_mean -> image mean 0004 % inv_model.gaussian_prior_likelihood.R_prior -> L*L' = inv(image covariance) 0005 % inv_model.gaussian_prior_likelihood.img_exp -> ( default = 2) 0006 % Parameters for data 0007 % inv_model.gaussian_prior_likelihood.Noise -> L*L' = inv(Noise covariance) 0008 % inv_model.gaussian_prior_likelihood.data_exp -> ( default = 2) 0009 % 0010 % Function to be used with inv_solve_mcmc 0011 0012 % (C) 2007 Nick Polydorides. License: GPL version 2 or version 3 0013 % $Id: prior_gaussian_likelihood.m 3122 2012-06-08 15:49:01Z bgrychtol $ 0014 0015 x_m = inv_model.gaussian_prior_likelihood.img_mean; 0016 L_x = inv_model.gaussian_prior_likelihood.R_prior; 0017 p_x = inv_model.gaussian_prior_likelihood.img_exp; 0018 L_n = inv_model.gaussian_prior_likelihood.Noise; 0019 p_n = inv_model.gaussian_prior_likelihood.data_exp; 0020 0021 img_residual= x - x_m; 0022 data_residual= y - J*x; 0023 0024 likelihood= exp(- norm(L_n * data_residual, p_n) ... 0025 - norm(L_x * img_residual, p_x));