An Attribute Extraction Algorithm based on Canny

Edge detection of images is a technique to extract information about changes in image properties, which is a hot topic in the field of image research and a prerequisite for image processing and computer vision. Image edges are the set of those pixels in an image that have a step change or roof-like change in the gray scale of surrounding pixels, and contain the most critical information in an image. And fast and efficient extraction of image edge information is crucial to the whole process of image processing. In order to improve the accuracy of acquisition in edge image information processing and eliminate the interference effects of edge burrs and shadow parts, this paper performs image edge extraction based on the Canny edge detection operator, and then fits a curve to the extracted contours by the Halcon correlation operator and derives the contour correlation properties. It is proved that this study helps to improve the extraction accuracy of subpixel edge image contour information and promotes the subsequent image processing.