7.3
The theory is applied to the parameter estimation for MRF object recognition where the form of the energy is derived based on MRFs. MRF modeling provides one approach to optimization-based object recognition [Modestino and Zhang 1989 ,Cooper 1990 ,Baddeley and van Lieshout 1992 ,Kim and Yang 1992 ,Li 1994a]. The MAP solution is usually sought. The posterior distribution of configurations f is of Gibbs
where Z is a normalizing constant called the partition function and
is the posterior energy function measuring the
global of f. In the following,
is defined and
converted to the linear form
.