基于多尺度多结构元的数学形态学边缘检测

Morphological edge detection based on multi-scale and multi-structuring elements

针对传统的边缘检测算子对噪声敏感问题,提出了一种基于多尺度多结构元素形态学边缘检测算子。该算子在传统形态学边缘检测的基础上,通过改变结构元素的形状和尺度,在很好抑制噪声的前提下,实现图像精细边缘提取。MATLAB仿真结果表明,该边缘检测算子具有更强的去噪能力,定位准确,保留了更多的图像细节,优于传统的边缘检测算子。

The detection results of traditional edge detection methods are sensitive to noise. Aiming at this problem, a morphological edge detec- tion algorithm based on multi-scale and multi-structuring elements is proposed. The algorithm can extract fine edge of the image in the premise of good suppression of noise by changing the scale and shape of the structure elements based on the traditional morphological edge detection. The MATLAB simulation results show that the edge detection operator has a stronger ability to remove noise and a more accurate orientation, more image details are retained. The method is better than the traditional edge detection operators.