Modified Adaptive Median Filtering

A modified adaptive median filtering algorithm is proposed, which can effectively remove the impulse noise and preserve the image details. The algorithm includes noise detection and noise removal. When detecting the noise, the minimum set difference(MSD) is introduced to reflect the correlation between pixel values in non-pollution set for distinguishing the high frequency components of a signal and its noise. And then the noise pixels are replaced by the median value. Comparisons of the proposed method with the standard median filter(SMF) and classical adaptive median filter(AMF) are made. The simulation results show that there are many advantages of the proposed method over the existing ones. Firstly, the noise detection rate is high. Secondly, the effect of noise reduction and details preservation are good, especially in the case of high noise density.