Rule based optimization of impulse noise remover fuzzy inference system

In this work, a rule-based training method for the optimization of a fuzzy inference system that is used as a noise removal operator is presented. In this method, only the parameters processed in the current epoch, rather than all parameters of the fuzzy inference system, are replaced with the new candidate solutions when examining the neighboring solutions in the search space. In the parameter based search, which is performed after the rule based search for the purpose of enhancing the solution obtained at the end of the optimization process, only the parameters under examination are adjusted while keeping the other parameters fixed and final result is obtained by repeating this operation for all parameters for a predetermined number of epoch cycles. In the proposed method, the MSE (mean square error) value of fuzzy model has been dramatically reduced without using mathematical morphology or a noise detector.