A new algorithm of image denoising based on stationary wavelet multi-scale adaptive threshold

In order to denoise while preserve image details better leading to a satisfactory result, so that it can be analyzed and applied subsequently, in view of advantages of well time-frequency characteristic, multi-resolution and decorrelation of stationary wavelet transform, this paper proposed a new algorithm of image denoising based on multi-scale and adaptive thresholding. In this algorithm: Firstly, use stationary wavelet to transform image. Then determine adaptive threshold of every decomposition progression according to the ratio of noise variance and wavelet coefficient variance. Secondly, process the wavelet coefficient matrice with threshold neighborhood sliding window and adaptively optimization wavelet coefficient processing window. Lastly, obtain resumed image through inverse transform. The experimental results show that, the algorithm can not only obtain clearer image edges but also denoise effectively compared to existing methods.