Efficient removal of impulse noise from highly corrupted digital images by a simple neuro-fuzzy operator

A new neuro-fuzzy operator for removing impulse noise from highly corrupted digital images is presented. The proposed operator is very simple and comprises two identical neuro-fuzzy filters combined with a postprocessor. The internal parameters of the filters are adaptively adjusted by training. Training of the filters is easily accomplished by using a simple computer generated artificial image. The fundamental advantage of the proposed operator over other operators is that it offers superior noise removal performance while at the same time efficiently preserving details and texture in the noisy input image. Experiments prove that the proposed operator may be used for efficient removal of impulse noise from highly corrupted images without distorting the useful information in the image.