基于Hausdorff距离的图像边缘检测方法  

A New Method of Edge Detection Based on Hausdorff Distance

作　　者：路游[1] 郭江涛[1] 孟庆鑫[1] 

机构地区：[1]中国石油大学(北京)地球物理与信息工程学院,北京102249

出　　处：《计算机技术与发展》2015年第8期71-74,79,共5页Computer Technology and Development

基　　金：国家自然科学基金资助项目(60873093)

摘　　要：边缘检测方法大多基于一阶微分或二阶微分,但微分有局部属性。用Hausdorff距离可以从整体上检测边缘。首先对图像进行重采样,将图像拆分成两个集合,然后利用Hausdorff距离构造的边缘强度映射给两个集合的每个点赋值以获得特征图。由于图像边缘特征的局部性,先由边缘强度映射作用于子图获得局部特征图,再由局部特征图获得原图的特征图。最后给出一种利用特征图确定图像边缘的计算方法。通过实验可以看出,该方法能够获得单像素宽度边缘,并对线性边缘有很好的检出效果。Most edge detection methods are based on first-order or second-order differential, but these are local methods. Using Hausdorff distance to detect the edge of an image is a holistic method. Firstly,resample the image, and split the image into two sets, then get the featung image by assigning a value for each point using the edge intensity mapping constructed by Hausdorff distance on the two sets. Since the edge features have local properties,in this paper,construct a map which can get local feature images using sub image and combine them into a feature image. Finally, a calculation method is given to get the edge image by feature image. It can be seen in experiment that this method can obtain the edge of a single pixel width, and have a good line-edge detection results.

关 键 词：图像处理 边缘检测 HAUSDORFF距离 特征图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]