基于Canny算子的改进图像边缘检测算法

图像的边缘检测是图像处理领域内最关键的技术之一.针对工件分拣中需要机器视觉精确的检测出其边缘信息,并且从噪声和其他无关信息中筛选出来,提出了一种改进的Canny算法对工件进行边缘检测.该算法利用双边滤波来替代高斯滤波进行图像预处理,从而不仅可以保留更多的图像边缘细节也可以有效的去除噪声.而后运用最大类间方差法(Otsu...

Improved Image Edge Detection Algorithm Based on Canny Operator

Image’s edge detection is one of the most critical technologies in the field of image processing. Aiming at the need for machine vision to accurately detect the edge information of workpieces,and in order to filter out the noise and other irrelevant information,this paper proposes an improved Canny algorithm for edge detection of workpieces. The algorithm first uses bilateral filtering to replace Gaussian filtering to perform image preprocessing,thereby effectively removing noise while preserving image edge details. Threshold segmentation is performed by using the maximum inter-class variance method(Ostu)to make target and background separation more accurate. Then,the binary image after threshold segmentation is expanded and corroded by mathematics morphology to obtain the morphological gradient map of the workpiece. The intersection of the difference image and the original threshold image is then detected by improved Canny algorithm.