一种新的全向变尺度边缘检测算法

New Edge Detection Method Based on Omni-directional and Multi-scale Mathematical Morphology

为了能够有效地抑制噪声对图像的影响,清晰准确的对图像进行边缘提取,提出了一种基于形态学的全向变尺度结构元素的边缘检测方法.该算子采用大尺度结构元素的开运算和闭运算去除噪声,采用小尺度结构元素提取图像的边缘.最后根据图像边缘特征信息调整权重,由不同的权重对各个方位得到的边缘检测图像进行加权合成计算.实验结果表明,该方法具有边缘定位准确轮廓清晰、抗噪能力强等优点.

In order to suppress image noise effectively and extract the edge clearly and accurately, a novel approach based on Omni-di- rectional and multi-scale mathematical morphology for edge detection is proposed in this paper. Opening operation and closing opera- tion of large scale structural elements are adopted for suppression of noise, while small scale structural elements are used for edge ex- traction. Finally, the weighting combination calculation of edge maps acquired under different directions is executed according to dif- ferent weights. The experimental results show that the improved algorithm has a great promotion in extracting edge information.