Image Denoising Method Based on Weighted Total Variational Model with Edge Operator

摘要

In order to eliminate image noise effectively, the weighted total variation algorithm based on edge detection is proposed. By calculating the amplitude of the edge operator of the image, accurate estimates of edge weights are achieved, and then the weight of the canny operator is used to weigh the Lagrangian multiplier, which is no longer a global variable, so that the filter has a better edge protection feature. Theoretical analysis and experimental results show that the method can remove noise while preserving the edge details of the image more completely. The step effects of the total variation model is effectively suppressed, and has a better performance in terms of structural similarity and the visual effect of image.