Issue No. 08 - August (1991 vol. 13)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.85674
<p>An estimator for estimating the parameters of a Markov random field X from inaccurate observations is introduced. The author considers first a Markov (Gibbs) random field X=(X/sub i,j/) on a lattice L=((i,j): i=1,2,. . .,n; j=1,2,. . .,m). The marginal distributions of (X/sub i,j/,X/sub i+u,j+v/) (u,v=-1,0,1) are first estimated from an image. Then, random fields X* are simulated with the probability of X*/sub i+u,j+v/)=b nearly equal to the estimate of P(X/sub i,j/=X/sub i+u/,=b). A simulation method similar to the Gibbs sampler is used. The parameters of the Markov random field model are estimated from the X*'s with the pseudolikelihood method.</p>
parameter estimation; picture processing; simulation-based estimator; hidden Markov random fields; probability; Gibbs sampler; pseudolikelihood method; Markov processes; parameter estimation; picture processing; probability
A. Veijanen, "A Simulation-Based Estimator for Hidden Markov Random Fields," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 13, no. , pp. 825-830, 1991.