边缘保留的图像滤波方法

An Edge-Preserving Image Filter

传统的高斯滤波在去除图像噪声的同时产生了边缘模糊的问题。本文通过对传统高斯滤波算法的改进,不仅考虑距离的影响,而且还考虑图像灰度值的影响。尤其是当邻域间像素的距离近并且灰度值相似时,则它们对结果有较大的影响。实验结果表明该方法在滤除图像噪声的同时又能保留图像边缘。

While the traditional Gaussian Filiter can reduce image noise; it may also blur image edges. This paper improves the traditional Gaussian filter by considering not only the spatial information, but also the range information of the image. Specifically,neighbors closer to and more similar to the pixel contribute more to the result.Experiments demonstrate that this method can preserve image edge well as well as reducing the noise,