首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于数学形态学的CR图像实时快速分割算法
引用本文:李哲,黄廉卿,李鹤.基于数学形态学的CR图像实时快速分割算法[J].光学技术,2007,33(1):6-10.
作者姓名:李哲  黄廉卿  李鹤
作者单位:1. 中国科学院长春光学精密机械与物理研究所,长春,130033;中国科学院研究生院,北京,100039;吉林大学计算机学院,长春,130026
2. 中国科学院长春光学精密机械与物理研究所,长春,130033
3. 吉林大学南岭校区医院放射科,长春,130026
摘    要:为实现CR图像实时快速分割,提出一种针对直方图的包络特征进行处理的新方法。首先计算出图像的直方图,然后对直方图进行形态学滤波,提取出直方图的包络,在此基础上对直方图的包络采用改进的基于标记的分水岭算法自动提取出最佳阈值。最后根据从直方图中提取出的、代表图像特征的阈值对CR图像进行实时快速分割,在采集完图像的同时就可以得出分割结果。通过实验和时间复杂度与空间复杂度分析表明,采用提出的算法通过减少运算量,可以快速分割出CR图像并提取出感兴趣区。

关 键 词:CR图像  直方图  最佳阈值  分水岭算法
文章编号:1002-1582(2007)01-0006-05
收稿时间:2006/1/4
修稿时间:2006年1月4日

A new quick segmentation method of CR images based on mathematical morphology
LI Zhe,HUANG Lian-qing,LI He.A new quick segmentation method of CR images based on mathematical morphology[J].Optical Technique,2007,33(1):6-10.
Authors:LI Zhe  HUANG Lian-qing  LI He
Abstract:A new method was proposed to segment CR images quickly.It deals with the envelop curve of histogram.First,the histogram of image was calculated,and then the histogram was filtered by mathematical morphology to extract the envelop curve.At last,the optimum threshold was calculated by watershed algorithm according to the envelop curve and then CR image was segmented quickly by calculated threshold that presents the feature of image.Experiments and the analysis of complex in time and space proved that this method is effective and quick to segment large scale CR images.Compared with other methods,the method can reduce the burden of computation,so it can segment CR images quickly.
Keywords:CR image  histogram  optimum threshold  watershed algorithm
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号