A Type-2 Fuzzy Logic Operator for Impulse Noise Removal from Digital Images

In this paper, a new detail-preserving neuro-fuzzy (NF) filtering operator based on typc-2 fuzzy logic tccniqucs for restoring digital images corrupted by impulse noise is presented. The operator is constructed by combining desired number of typc-2 NF filters, defuzzifiers and a postprocessor. All NF filters in the structure of the operator are Sugeno type first order type-2 interval fuzzy inference systems. Internal structures of the NF filters are identical to each other. Simulation results indicate that the proposed operator offers superior performance in removing impulse noise from images while effectively preserving image details and texture.