基于非线性滤波的边缘检测算法

Algorithm of edge detection based on nonlinear filtering

线性滤波对于边缘检测的去噪处理存在着使边缘模糊、边缘检测定位精度降低的问题。为解决这个问题,分析了两种非线性滤波,即各向异性扩散滤波和双边滤波,分别将两种滤波应用在边缘检测的滤波过程。通过对比实验结果表明:非线性滤波方法可以提高边缘检测的准确率,得到更有效的边缘信息。

Linear filtering used for smoothing the image before the edge detection may lead to blurry edge and higher edge location error. To solve these problems, this paper proposed two kinds of nonlinear filtering such as anisotropic diffusion filtering and bilateral filtering, also, applied them to edge detection respectively, by contrastable experiment results indicate that the rate of accuracy of edge detection can be enhanced and a much better edge detection effect is obtained.