Rule based optimization of type-2 fuzzy inference system used at impulse noise removing

In this work, a method involving the use of a type-2 fuzzy inference system for impulse noise removal from digital images is presented. In the presented work, parameters of the type-2 fuzzy inference system are optimized by the Clonal Selection Algorithm adopting a rule based approach. In the rule based approach, parameters of the type-2 fuzzy inference system are separated by the rules in the system and only parameters of the current rule are optimized in each epoch. With this approach, performance of the heuristic algorithm is considerably improved. In univariate approach applied after the rule based approach, all parameters are kept fixed and the final result is obtained by optimizing the parameters one by one within a narrower interval. Experimental results show that the MSE (mean square error) value of the type-2 fuzzy filter has been dramatically reduced by using the proposed method.