一种改进的形态学边缘检测算法  

An improved morphological edge detection algorithm

作　　者：张梦 张小美[2] 黄颖辉 ZHANG Meng;ZHANG Xiaomei;HUANG Yinghui(Nantong Academy of Intelligent Sensing,Nantong 226000,China;School of Information Technology Science,Nantong University,Nantong 226000,China)

机构地区：[1]南通智能感知研究院智能遥感事业部,江苏南通226000 [2]南通大学信息技术科学学院,江苏南通226019

出　　处：《广西科技大学学报》2021年第2期72-77,共6页Journal of Guangxi University of Science and Technology

基　　金：南通市科技攻关项目(通CT200205)资助.

摘　　要：为提取出更丰富流畅、定位更准确的边缘信息,基于多尺度多方向结构元素,引入信息熵加权系数,改进了形态学边缘检测算法.首先,为去除图像噪声,选定2种不同尺度的结构元素进行形态学开闭运算;然后,利用4种不同方向的结构元素进行形态学边缘检测,可以获得4幅不同方向结构元素下的边缘图像;再根据每幅边缘图像的信息熵来确定权值,并将这些边缘图像按照比例进行加权求和即可得到较为理想的边缘图像.仿真实验证明:改进的形态学边缘检测算法具有很强的抗噪性能,而且检测到的边缘信息更完整流畅,具有一定的适用性和优越性.To extract more abundant and smooth edge information and more accurate positioning,based on multi-scale and multi-directional structural elements,the weighted coefficient of information entropy is introduced to improve the morphological edge detection algorithm.Selecting two different scale structure elements can reduce the noise of the image.Using four different direction structure elements,we can get the edge image of different direction structure elements.According to the information entropy of each edge image,we can determine the weight,and then we can get the ideal edge image by weighted sum of these edge images according to the proportion.Simulation results show that the improved morphological edge detection algorithm has strong anti noise performance,and the edge information detected is more smooth and complete,which has certain applicability and superiority.

关 键 词：多尺度多方向 结构元素 信息熵 形态学边缘检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]