An Improved Algorithm of Adaptive Fuzzy Image Enhancement

Aiming at the limitation of the fuzzy neural network method for image enhancement presented by Dr. Russo, whose parameter was fixed and not flexible, a novel method of adaptive parameter selection was proposed in this paper. By calculating the difference between the gray value of each pixel and the median of its neighborhood, select adaptively smooth and sharp parameters. Compared with the method of Russo and others, experimental results show that the performance of the novel method is much better and makes the enhancement more detailed, and the complexity of the algorithm is obviously lower.