Adaptive Filter Algorithm Based On Human Visual System

This paper simply introduces the emergence, development, basic working theory and characteristics of digital image filtering technology. The typical median filter can remove the impulse noise, but it also has many disadvantages. There are many improved median filters firstly suggested to overcome the problems.To overcome the drawback of the standard median filter, an adaptive median filter algorithm based on human vision system is proposed in this paper. In the algorithm, it determines possible noisy pixels according to the noisy threshold, the noisy sensitive coefficient which is based on human vision system, then the noisy pixels is removed by the iterative median filter algorithm. It has been proved that this algorithm is better than these former algorithms through the contrast of image peak signal to noise ratio.However, there are many different noise in one image usually .The most common type are the impulse noise and Gaussian noise. It will be not easy to remove mixed noise in a single filter. To remove mixed impulse noise and Gaussian noise in digital images, a mixed filter algorithm based on the adaptive median filter algorithm and fuzzy mean filter algorithm is proposed. First it determines and moves the impulse noisy pixels by the adaptive median filter algorithm based on human vision system. Then a detail-preserving fuzzy filter is adopted to reduce Gaussian noise contained in the pixels. The algorithm has better filtering performance than the standard filters and other improved mixed filters.