Mixed noise correction in Gray images using fuzzy filters

This paper presents Gaussian and Impulse noise filters for eliminating mixed noise in images. For Gaussian filter, the fuzzy set called "small" is derived to represent the disorder in a pixel arising out of neighborhood corrupted with Gaussian. The expression for correction is developed based on the intensity of the central pixel and the membership function. Similarly, the correction for the Impulse noise is developed by finding the middle ranking pixels in the neighborhood of the central pixel. The difference between the average of the middle ranking pixels and the central pixels is used to evaluate the membership function which when multiplied by the difference gives the correction. Consequently, the presence of noise is detected by finding the aggregate of the four highest memberships of the neighborhood pixels. If this aggregate is more than the threshold then there is Gaussian noise otherwise impulse noise. Accordingly, the corrupted pixel will be corrected by the correction term. The results are found to be satisfactory.