基于数学形态学和Canny算子的边缘提取方法  

Edge detection method based on mathematical morphology and canny algorithm

作　　者：何新英[1] 王家忠[1] 孙晨霞[1] 常淑惠[1] 周桂红[1] 

机构地区：[1]河北农业大学信息学院,河北保定071001

出　　处：《计算机应用》2008年第2期477-478,483,共3页journal of Computer Applications

基　　金：河北省教育厅资助项目(Z2006433);河北农业大学非生命学科科研基金

摘　　要：提出了一种基于数学形态学和Canny算子的边缘提取方法。该方法利用数学形态学开运算估计背景,将原始图像与背景进行几何运算,在处理后的图像上运用Canny算子提取边缘。实验结果表明,该方法明显优于传统的经过中值滤波后再进行Canny算子的边缘检测效果,为后续的特征提取、目标识别提供了良好的基础。A new edge detection method was put forward based on mathematical morphology and Canny algorithm. The background of the image was estimated by morphological opening and then calculated together with the original image by geometric operations. Finally, the Canny edge detection algorithm was applied to the processed image. The experimental results show that the proposed approach is obviously superior to the traditional Canny edge detection method with median filter, and provides good foundation for feature extraction and object recognition.

关 键 词：边缘检测 数学形态学 噪声滤除 中值滤波 CANNY算子 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]