一种全方位多角度自适应形态滤波器及其算法

A kind of omni-directional multi-angle structuring elements adaptive morphological filters

根据形态滤波器的结构元特性,结合形态开—闭(闭—开)组合运算及自适应算法,建立了一种能有效去除复杂纹理图像中的各种噪声,并较好的保持图像细节的方法。实验证明,这种全方位多角度自适应形态滤波器与现有的中值滤波器、全方位结构元形态闭—开最小、开—闭最大滤波器等非线性滤波器相比较有更好的降噪性能及细节保护能力,扩展了形态滤波器在滤除高斯噪声方面的应用,提高了形态滤波器的适应性。

According to the structure characteristic of the morphological filter and combining the open-closing (close-opening) compound operation with adaptive arithmetic, this paper presents a kind of method that can not only efficiently removed various noise in images which have the complex texture but also preserved the detail better. The results of simulation show that it is superior to the standard median filter, the maximal, minimal morphological filter with onmi-directional structuring elements in the aspect of the noise removal, thereby extending the application of the morphological filters in removing the Gaussian noise. What is the most important is that this algorithm can keep the details of images more effectively.