| 基于数学形态学的医学图像分割 |
| |
| 引用本文： | 王蜀,李永宁,陈楷民,黄戈. 基于数学形态学的医学图像分割[J]. 计算机应用, 2005, 25(10): 2381-2382 |
| |
| 作者姓名： | 王蜀 李永宁 陈楷民 黄戈 |
| |
| 作者单位： | 四川大学,计算机学院,四川,成都,610064;四川大学,计算机学院,四川,成都,610064;四川大学,计算机学院,四川,成都,610064;四川大学,计算机学院,四川,成都,610064 |
| |
| 摘 要： | 采用分水岭算法对医学图像进行分割，并针对其容易产生过分割的缺点，作了两点改进：首先对原始图像进行自适应加权的多尺度形态滤波，然后引入浮点活动图像作为分水岭算法的输入。实验表明，该方法算法简单，能有效地抑制过分割现象，得到较好的分割效果。
|
| 关 键 词： | 数学形态学 分水岭算法 自适应加权的多尺度形态滤波 浮点活动图像 |
| 文章编号： | 1001-9081（2005）10-2381-02 |
| 收稿时间： | 2005-04-13 |
| 修稿时间： | 2005-04-132005-06-22 |
Medical image segmentation based on Mathematical Morphology |
| |
| WANG Shu,LI Yong-ning,CHEN Kai-min,Huang Ge. Medical image segmentation based on Mathematical Morphology[J]. Journal of Computer Applications, 2005, 25(10): 2381-2382 |
| |
| Authors: | WANG Shu LI Yong-ning CHEN Kai-min Huang Ge |
| |
| Affiliation: | School of Computer Science, Sichuan University, Chengdu Sichuan 610064, China |
| |
| Abstract: | In this paper, the watershed algorithm to segment medical images was introduced. The two improved methods considering the over-segmentation phenomena of watershed algorithm were presented. First, get the original image through multi-scale morphological filter with auto-adapted determinations weights, and then, introduced a floating-point active image as the input of watershed algorithm. Experiments show that the algorithm is very simple, and can restrain the over-segmentation phenomena effectively, so can obtain good results. |
| |
| Keywords: | mathematical morphology watershed algorithm: multi-scale morphological filter with auto-adapted determinations weights floating-point active image |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
|
