自适应多结构元形态学边缘检测方法

Adaptive Morphology Edge Detection Based on Multi-structural Elements

对自适应选取结构元权值以及如何有效去除混合噪声是多结构元形态学边缘检测中尚待解决的两个问题,在深入研究各种形态学边缘检测方法的基础上,提出了基于灰度距离逻辑函数和基于边缘方差两种自适应多结构元形态学边缘检测方法。首先对原始图像进行最优阈值分割二值化,其次从灰度距离和边缘方差两个角度分别实现结构元的自适应选取,最后选择形态算子进行边缘检测。方法具有更好的抗噪性和灵活性,能更加精确的体现原有图像的边缘方向信息。通过仿真实验,验证了方法的可行性和有效性。

How to select the weights of structural elements and eliminate complex noise are two problems to be solved in edge detection. This paper analyses the measures of multi - structural elements in existence, then two evaluations based on gray distance and edge variance are proposed. The method has three steps. First, an optimization threshold is selected and used to transform the originnal image into binary image. Secondly, two adaptive algorithms are proposed for selecting the weights of multi - structural elements. Finally, morphology operator is selected to de- tect the binary image. The results show that the method has better noise immunity and flexibility. It can more accu- rately reflect the direction of the edge of original image information, and the practicability and efficiency of the approach are demonstrated.