期刊
SIGNAL PROCESSING
卷 90, 期 10, 页码 2851-2862出版社
ELSEVIER
DOI: 10.1016/j.sigpro.2010.04.009
关键词
Angles; Curvature; Edges; Jump-preserving surface estimation; Local smoothing; Nonparametric regression; Surface estimation
资金
- NSF
Image denoising is important in image analysis. It is often used for pre-processing images so that subsequent image analysis is more reliable. Besides noise removal, one important requirement for image denoising procedures is that they should preserve true image structures, such as edges. This paper proposes a novel denoising procedure which can preserve edges and major edge features (e.g., angles of the edges). Our method is based on nonparametric estimation of a discontinuous surface from noisy data, in the framework of jump regression analysis, because a monochrome image can be regarded as a surface of the image intensity function and such a surface has discontinuities at the outlines of objects. Numerical studies show that this method works well in applications, compared to some existing image denoising procedures. (C) 2010 Elsevier B.V. All rights reserved.
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。
推荐
暂无数据