基于MATLAB的Canny图像边缘检测优化与实现

Optimization and Implementation of Canny Image Edge Detection Based on MATLAB

图像边缘是图像最基本也是最重要的特征,是图像处理目前研究的一个热点。各种算子在图像边缘识别方面各有优缺点,其中Canny算子具有不易受噪声影响且可以检测到真正弱边缘的优势。通过自行优化Canny边缘检测的处理过程和算子,发现Canny算子对滤波参数的选择和高低阈值的取值范围比较敏感。与MATLAB内置Canny边缘检测API相比,此方法可以提取更多的图片信息,减少失真。

Image edge is the most basic and important feature of the image,and it is a hot spot in image processing at present.Various operators have their own advantages and disadvantages in the aspect of image edge recognition.Thereinto,Canny operator has the advantage that it is not easy to be affected by noise and can detect the real weak edges.By self optimizing the processing procedure and operator of Canny edge detection,it is found that the Canny operator is sensitive to the selection of filtering parameters and the value range of high and low thresholds.Compared with Canny edge detection API built in MATLAB,this method can extract more picture information and reduce distortion.