鲁棒的形态学彩色图像边缘检测算法

针对传统边缘检测算子对噪声敏感的缺点，提出一种新的基于数学形态学的彩色图像边缘检测算法。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，设计出一种多尺度、多结构元素的抗噪型边缘检测算子，利用新算子对R、G、B三个分量分别检测出图像的边缘分量，对三个边缘分量进行融合得到最终的彩色边缘信息。仿真实验表明，该方法得到的边缘轮廓清晰，边缘定位精度较高，比传统的边缘检测方法具有更好的噪声鲁棒性和边缘细节保护能力。

Robust color image edge detection algorithm based on mathematical morphology

The traditional edge detection operators have high sensitivities to noise. A novel color image edge detection algorithm based on mathematical morphology is proposed. On the basis of edge detection operators of morphology and combining with morphological dilation and morphological erosion, a new anti-noise edge detection operator based on multi-scale and multi-structuring elements is obtained. The proposed method is respectively executed to red, green and blue to get edge information of three components. The color edge information is obtained by combining three components’ edge information. Experimental results demonstrate the feasibility and effectiveness of the proposed algorithm. It can obtain clear color edge and high detection accuracy. The algorithm has better ability of preserving the edge details and better robustness to noises than traditional methods.