Cited by
- BibTex
- RIS
- TXT
Though image denoising has experienced rapid development, there remain problems to be solved such as preserving the edge and meaningful details in image denoising. In this paper, we focus on this hot issue. Considering the parameter in original method is a constant, we introduce a new adaptive parameter selection based on EPLL (Expected Patch Log Likelihood) by the use of image gradient and the local variance, which varies with different regions of the image. What’s more, for solving staircase effect which common in anisotropic diffusion models, we add a gradient fidelity term to release it. The experiment shows that our proposed method proves the effectiveness not only in vision but also on quantitative evaluation.
}, issn = {1746-7659}, doi = {https://doi.org/}, url = {http://global-sci.org/intro/article_detail/jics/22367.html} }Though image denoising has experienced rapid development, there remain problems to be solved such as preserving the edge and meaningful details in image denoising. In this paper, we focus on this hot issue. Considering the parameter in original method is a constant, we introduce a new adaptive parameter selection based on EPLL (Expected Patch Log Likelihood) by the use of image gradient and the local variance, which varies with different regions of the image. What’s more, for solving staircase effect which common in anisotropic diffusion models, we add a gradient fidelity term to release it. The experiment shows that our proposed method proves the effectiveness not only in vision but also on quantitative evaluation.