形态学和Otsu方法在Canny边缘检测算子中的应用

Application of Morphology and Otsu Method in Canny Edge Detection Operator

传统的Canny边缘检测算子在高斯滤波方差和滞后阈值的选择上需要人工指定,不具备自适应能力.高斯滤波方差影响图像的去噪和边缘保持效果,用形态学平滑代替高斯滤波,可以保留边缘信息并去除噪声的影响;滞后阈值影响虚假边缘现象的强弱和真实边缘的连续性,利用Otsu方法对阈值进行自适应设定,使检测出的边缘更加连续并减少虚假边缘的存在.实验结果表明,对传统的Canny算子有一定程度的改进.

The traditional Canny edge detection operator requires human intervention,does not have the adaptive ability in the variance of Gaussian filtering and the lag threshold.The variance affects the edge preserving and de-noises ability effect.Morphological smoothing replaces Gaussian filtering,can not only maintain the edge information but also reduce noise impact.The lag threshold affects degree of the fake edges phenomenon and continuity of the real edges,Otsu method can specify the threshold adaptively,the edge detected is more continuous,and can decrease the false edges.With the experimental results,it has a certain degree of improvement on traditional Canny operator.