基于多结构元素串行形态滤波器的研究

The Research of Serial Morphological Filters Based on Multiple Structuring Elements

针对数学形态学在图像去噪处理中的应用,采用多结构元素,构造了一类串行级联式形态滤波器。这类滤波器不仅可以有效地抑制图像中的噪声,而且较好地保持图像的几何结构特性。实验结果表明该方法与传统的形态开-闭和闭-开算法相比,提高了图像的信噪比,降低了均方误差,图像视觉效果显著提高。

Based on the application of the image denoising in mathematical morphological, a class of serial cascade morphological filters is constructed by using multiple structuring elements. These filters can not only efficiently suppress noise images but also preserve the geometrical features of images. The results of computer sim- ulation show that the method can improve the signal-to-noise ration （SNR）, depress the mean square error, and noticeably improve the image＇s visual effect, comparing with the traditional open-closing and close-opening algorithm in mathematical.