4.6 Article

An adaptive VPDE image denoising model based on structure tensor

期刊

MULTIMEDIA TOOLS AND APPLICATIONS
卷 78, 期 19, 页码 28331-28354

出版社

SPRINGER
DOI: 10.1007/s11042-019-07912-7

关键词

Image denoising; Structure tensor; Total variation; Norm parameter; Partial differential equation

向作者/读者索取更多资源

Image denoising is one of the challenging topics in image processing. Since the formation mechanism of the degraded image is unknown, it is difficult to achieve effective image denoising. Most existing denoising methods are easy to blur the edges of the image so that it is difficult to maintain more image detail information. In recent years, partial differential equation (PDE) has been applied to image denoising, which has shown good application prospects. However, the image denoising methods based on PDE are easy to appear staircase effect and edge blur, and can not achieve satisfactory denoising effect. To avoid some problems, an adaptive variational PDE (VPDE) image denoising model based on the structure tensor is proposed and analyzed. In the proposed model, since the structure tensor can provide more local structural information and direction information of the gradient, the eigenvalues of the structure tensor of an image are used to construct the norm parameter. Through theoretical analysis and experiments, we can confirm that the proposed norm parameter has the following adaptive characteristics: (1) In the flat region of the image, the proposed norm parameter tends to 2, so which has the characteristic of isotropic diffusion. (2) At the edge region of the image, the norm parameter tends to 1, and which spreads only along the tangential direction of the image edge. The experimental results from both subjective and objective aspects show that using these adaptive characteristics, the proposed image denoising model can effectively avoid staircase effect, preserve the image details, and obtain satisfactory denoising effect.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据