Fuzzy method for image filtering

This paper presents a new method for image spatial filtering using fuzzy concepts and convolution matrix. The spatial meaning of the pixels from a window determines the main pixel of this window. Using fuzzy 3-D interpolation, the representative median pixels determine the intensity value of the image pixel. Using a knowledge-based model the fuzzy 3-D interpolation gives a natural solution for the coefficients function set of the linear interpolation function. The proposed method was tested for different distorted or noisy images. The obtained results using matrix convolution filtering are compared with these obtained with fuzzy filtering.