基于多结构元素的数学形态学边缘检测算法

Morphological Edge Detection Algorithm Based on Multi-structuring Elements

针对传统边缘检测算子对噪声敏感的不足,提出了一种基于多结构元素的数学形态学边缘检测算法。该算法在传统形态学边缘检测算子的基础上,通过综合形态膨胀和形态腐蚀,得到一种新的抗噪型边缘检测算子,利用多结构元素提取图像的边缘特征,即使在噪声条件下,也能获得较为理想的图像边缘。实验结果表明,与传统的边缘检测算子相比,该方法边缘检测精度高,且具有良好的噪声鲁棒性。

To improve the lack of noise - sensitive for conventional edge detection operators, a morphological edge detection algorithm based on multi - structuring elements is proposed. On the basis of edge detection operators of morphology and combining with morphological dilation and erosion, a new anti - noise edge detection operator is obtained. The more ideal image edges under the environment of existing noise are obtained by extracting the edge characteristics of image with multi - structuring elements. Experimental resuits demonstrate the feasibility and effectiveness of the proposed algorithm; meanwhile, it has higher detection accuracy and better robustness to noises than conventional methods.