An Improved Fuzzy Image Enhancement Algorithm

An effective method for fuzzy image enhancement was presented by Russo, which was controlled by tuning of one parameter. The fixed parameter was used for the entire image resulting in over blurring or sharpening of image features in some parts of the image. On the basis of these, in this paper, we applied Russo's algorithm on different kinds of noise and proposed an efficient method to obtain the parameter values adaptively. Firstly, each pixel went through a phase of smoothing and then followed by a phase of combining smoothing and sharpening; Secondly, to effectively enhance image, each pixel local feature was adoptively assigned different parameter values by evaluating pixel local features through a fuzzy membership function; Finally, compared with Russo's method and other methods, experimental results indicated that the proposed method could achieve better performance than traditional methods for the enhancement of images corrupted with impulse and Gaussian noise.