| 克服分水岭算法过分割的方法 |
| |
| 引用本文： | 魏光杏,吴锡生.克服分水岭算法过分割的方法[J].江南大学学报(自然科学版),2008,7(1):38-41. |
| |
| 作者姓名： | 魏光杏 吴锡生 |
| |
| 作者单位： | 1. 江南大学,信息工程学院,江苏,无锡,214122;滁州职业技术学院,信息工程系,安徽,滁州,239000
2. 江南大学,信息工程学院,江苏,无锡,214122 |
| |
| 摘 要： | 分水岭算法的不足在于它的过分割结果,即生成大量小的封闭区域,使目标物体淹没其中.文中给出了模糊关系与模糊C均值聚类算法相结合的方法,利用了模糊关系合并相似区域,有效地克服了分水岭算法的过度分割问题.经实验验证,该方法大大提高了图像分割质量.
|
| 关 键 词： | 分水岭 模糊关系 图像分割 |
| 文章编号： | 1671-7147(2008)01-0038-04 |
| 修稿时间： | 2006年8月15日 |
A New Method of Overcoming the Over- Segmentation in Watershed Algorithms |
| |
| WEI Guang-xing,WU Xi-sheng.A New Method of Overcoming the Over- Segmentation in Watershed Algorithms[J].Journal of Southern Yangtze University:Natural Science Edition,2008,7(1):38-41. |
| |
| Authors: | WEI Guang-xing WU Xi-sheng |
| |
| Abstract: | Watershed algorithm is automatic segmentation scheme to generate closed outlines,which may give rise to over-segmentation,i.e.,numerous small segmented closed regions that blur the target contours or shapes.The method based on the application of the Fuzzy C- means algorithm together with composition of fuzzy relations is proposed,which employs the composition of fuzzy relations to group together similar regions and overcomes the over-segmentation efficiently.The experimental results validate its good performances of the method. |
| |
| Keywords: | watershed fuzzy relation image segmentation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
