Image Denoising With Strong Noise Base On Curvature Filters

In order to overcome the defect of the curvature filtering method in image denoising capability, and to remove the noise of the strong noise image while maintaining the image edge and detail features, an image denoising with strong noise image based on curvature filter is proposed in this paper. The traditional curvature filtering achieves the fast convergence by implicitly calculating the image curvature. However, only the minimum triangulation plane projection operator is used in the iterative process, which results in denoising effect is poor and incomplete. This paper presents enhanced denoising projection operator and modified regularization energy function, to achieve the purpose of enhancing the denoising ability while protecting the edges of image. Experimental results show that compared with the traditional variational method, the proposed algorithm has a significant effect on denoising images with strong noise, and has a good peak signal-to-noise ratio and structural similarity. Implicitly calculated image curvature is adopted, and the processing speed of the algorithm is close to the curvature filtering algorithm.