|
|||||
|
|
| 一种改进的分水岭分割算法 | |
| 引用本文： | 冷美萍,鲍苏苏,孟祥玺,彭丰平.一种改进的分水岭分割算法[J].贵州师范大学学报(自然科学版),2010,28(1):62-65. |
| 作者姓名： | 冷美萍 鲍苏苏 孟祥玺 彭丰平 |
| 作者单位： | 1. 华南师范大学,计算机学院,广东,广州,510631 2. 贵州财经学院,信息学院,贵州,贵阳,550004 3. 华南师范大学南海校区,计算机工程系,广东,佛山,528225 |
| 基金项目： | 国家高技术研究发展计划(863)(No.2006AA02Z346);;广东省自然科学基金团队项目(6200171)等资助 |
| 摘 要： | 为了提取人脑CT图像中的脑部组织,提出了一种改进的分水岭算法,首先采用K-means聚类算法对图像进行初始分割,从而有效地抑制了由图片表面的灰度变化引起的过分割,使边缘定位更加准确;然后在聚类图像的梯度图上利用自动阈值法增强其对比度,进行分水岭分割。最后为了避免过分割现象,对分割后的图像进行了相似区域合并。实验表明该方法简单有效,能够得到符合人类视觉系统特性的分割结果。 |
| 关 键 词： | CT图像 K-means聚类 分水岭分割 梯度 区域合并 |
A method of improved watershed segmentation algorithm |
|
| LENG Mei-ping,BAO Su-su,MENG Xiang-xi,PENG Feng-ping.A method of improved watershed segmentation algorithm[J].Journal of Guizhou Normal University(Natural Sciences),2010,28(1):62-65. | |
| Authors: | LENG Mei-ping BAO Su-su MENG Xiang-xi PENG Feng-ping |
| Institution: | 1.School of Computer/a>;South China Normal University/a>;Guangzhou/a>;Guangdong 510631/a>;China/a>;2.School of Information/a>;Guizhou College of Finance and Economics/a>;Guiyang/a>;Guizhou 550004/a>;3.Department of Computer Engineering/a>;Foshan/a>;Guangdong 528225/a>;China |
| Abstract: | In order to extract brain tissue from human brain CT image,we propose an improved watershed algorithm.Firstly,we use K-means clustering to produce a primary segmentation,thus effectively inhibiting over-segmentation caused by grey level change of the surface of picture,which can be located at the contour more accurately.Then the improved watershed segmentation algorithm makes use of automated thresholding on the gradient magnitude map.Finally,regions merging algorithm is applied to avoid over-segmentation.T... |
| Keywords: | CT image K-means clustering watershed segmentation magnitude region merging |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |