Using genetic algorithm optimizing stack filters based on MMSE criterion

In this paper, the problem of optimizing stack filters is changed into a one-zero knapsack problem based on the minimum mean square error (MMSE) criterion. The optimization of stack filters is realized by solving this knapsack problem with genetic algorithm (GA). Optimal stack filters are designed to process the images corrupted by impulsive noise in this paper. The computer simulated experiments show that the suppressing noise capability of the optimal stack filters based on the MMSE criterion is better than that of the optimal stack filters based on the minimum mean absolute error (MMAE) criterion. Moreover, the optimizing performances of simple genetic algorithm and adaptive genetic algorithm are discussed in this paper.