The Design of Evolvable Hardware Image Filters Using Fuzzy Sets

This study deals with the design of evolvable hardware(EHW) based image filters using fuzzy sets. Two indicators, similarity and divergence, are defined as fuzzy sets for describing the relations of pixels contained in a sliding window. In the proposed method, each pixel to be recovered is analyzed by the fuzzy sets and labeled as the associated noise type. Multiple EHW-based image filters, each of which is trained supervisedly by the pixels belonging to the same noise type, are built simultaneously. In the recovery phase, the recovering value is the fuzzy weighted summed of the outputs from the filters. Because each image filter is dedicated to a specific type of noise, it can recover pixels of the noise type more accurately. With the proposed method, the efficiency of training EHW models and accuracy of image filtering are both improved. This paper evaluates and compares the performance of the proposed method with other ones.