Adaptive fuzzy weighted mean filter for removal of Gaussian noise

To remove the Gaussian noise in the image effectively, the adaptive fuzzy weighted mean (AFWM) filter is proposed. In this algorithm, the corruption degree of image by the noise is first estimated. According to the corruption degree, the improved mean filter is then adopted. When the corruption degree is low, the adaptive weighted mean (AWM) filter with the small filtering window is applied. When it is moderate, the AWM filters with the small filtering window and the big one are applied successively. When it is high, the above AWM filters are first adopted and then the fuzzy weighted mean (FWM) filter with the small filtering window is applied to suppressing the Gaussian noise in the image. Simulations show that the AFWM filter can suppress Gaussian noise effectively while preserving the fine details very well and has better filtering performance than the standard mean filter and other improved mean filters.