适用于医学图像的模糊边缘检测改进算法  

Improved fuzzy edge examination algorithm using medical image

作　　者：何鹏[1] 徐春伟[1] 张裕[1] 

机构地区：[1]齐齐哈尔大学通信与电子工程学院,黑龙江齐齐哈尔161006

出　　处：《计算机工程与应用》2009年第18期231-233,共3页Computer Engineering and Applications

基　　金：黑龙江省教育厅科学技术研究项目No.11521331~~

摘　　要：边缘检测是医学图像预处理中最重要的内容之一,系统地分析了Pal.King模糊边缘检测算法的不足,提出一种适用于医学图像的新型模糊边缘检测算法。该算法使用遗传算法对传统Otsu算法进行优化来确定阈值参数,对待测图像所对应的模糊特征平面通过基于此阈值定义的隶属函数来提取,并且对图像进行分区模糊增强和平滑处理以达到更好的边缘检测效果。仿真结果表明,针对所要处理的医学图像,与几种经典的处理方法相比,该算法能够提取出更加真实和完整的边界信息。Edge detection is one of the most important elements in medical image processing.This paper analyzes the drawback of Pal.King fuzzy edge detection algorithm,an improved algorithm of medical image is presented.The algorithm presents a scheme for optimal traditional Ostu algorithm using genetic algorithms to definite threshold parameters,a definition of membership function according to this threshold for extract the fuzzy characteristics plane is corresponded by the treatment image,to do fuzzy enhancement with separated regions and smooth processing of image up to the better edge detection effect.For the medical image which needs to be processed,the experiment indicates,this algorithm can withdraw boundary information true and integrity compared with some classic methods.

关 键 词：边缘检测 模糊增强 医学图像 阈值优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]