摘要
提出了一种新的图象平滑方法。该方法利用区域模板和线性模板 ,将图象中的高频噪声和合理的边界结构通过采用不同的模板进行平滑 ,达到了既去除噪声 ,又保存图象边界的目的 ,为图象的预处理提供了一种很好的方法。
Existing image smoothing methods can not preserve the edges in an image while removing noise. We present a new method——preserving edge smoothing (PES), to solve this problem. We first design several region masks (Fig.2) and linear masks (Fig.3). By using different region masks, we can determine which region a pixel in the image belongs to, then noise can be removed and the region edges can be preserved to a certain degree by substituting a region′s mean value for its pixel′s value. At the same time, we can use linear masks to distinguish the pixels of edges and noise pixels, thus preserving the edges. The experimental results (Figs.7 and 9) show that this method can not only remove noise in image regions, but also preserve the edges.
出处
《西北工业大学学报》
EI
CAS
CSCD
北大核心
2000年第1期102-105,共4页
Journal of Northwestern Polytechnical University