On the design of neighboring fuzzy median filter for removal of impulse noises

The digital images are easily affected by the noises; hence the image filters are often regarded as preprocessing of image processing system. If the image has serious damage or high-noise, the traditional image filters are usually unable to handle well. The application of median filter has been investigated. As an advanced method compared with standard median filtering, the adaptive median filter performs spatial processing to preserve detail and smooth non-impulsive noise. In this paper, a novel filter method, a neighboring selection method based on the fuzzy median filter, is proposed to improve the existing filter so that more image details can be preserved while effectively suppressing impulse noise. The proposed filter mechanism is composed of a new efficient noise eliminator based on the ideal of image rotation and LVQ network. Extensive simulation results demonstrate that our scheme performs significantly improve the default filter.