We propose an optimization method for belief propagation. First we mathematically show that the belief propagation algorithm can be optimized by imposing a reasonable restriction on the conditional probability tables in a Bayesian network. Then we demonstrate the efficiency of the proposed algorithm with experiments. Compared to the previously derived approximate algorithm, the proposed algorithm has the following features: 1. the proposed algorithm calculates more accurate maximum posterior marginal values, 2. similar to the approximate algorithm, its execution time grows only linearly against the number of edges, and 3. the proposed algorithm is slower than the approximate algorithm, but the difference between their execution time is less than twice.