基于Canny算法的自适应边缘检测方法
卞桂平;秦益霖
【摘 要】图像边缘检测是数字图像处理的重要组成部分.传统的Canny边缘检测算子存在高斯滤波函数方差和阈值选取上的缺陷,本文提出了一种基于改进canny算子的图像边缘检测算法.首先运用复合形态学滤波取代高斯滤波,然后运用Otsu算法进行高低双阈值的自适应选取;最后连接边缘并运用数学形态学对边缘进行细化.实验结果表明,改进算法具有良好的抗噪性能和较好的检测效果.%Image edge
detection is an important part of digital image processing. The traditional
Canny edge method without the adaptive ability in the variance of
Gaussian filtering and threshold, this paper proposes an image edge
detection algorithm based on improved Canny operator. Firstly, this
method uses compound morphology smoothing replaces Gaussian
filtering; then this method uses the Otsu method to calculates the optimal
high and low dual-threshold; finally, connecting edge and using the
morphology to thinning the image detection edge. Experimental results
prove that the improved algorithm has a good anti-noise function and a