From (14), we need to compute the prior probability of the class and the likelihood probability of the observation. Since

It is also assumed that the pixel intensity

(16) |

Based on the conditional independence assumption of

which can be written as

with the

and the constant normalization term . It is easy to show that

where

is the

Although mathematically simple, this type of MAP estimation clearly presents a computationally infeasible problem. Therefore, optimal solutions are usually computed using some iterative optimization (minimization) techniques. In this paper, we adopt a