| 基于人工免疫的灰度图像多阈值自动分割 |
| |
| 引用本文： | 李彬,田联房,毛宗源.基于人工免疫的灰度图像多阈值自动分割[J].计算机工程与设计,2007,28(1):106-108. |
| |
| 作者姓名： | 李彬 田联房 毛宗源 |
| |
| 作者单位： | 华南理工大学自动化科学与工程学院 广东广州510640 |
| |
| 基金项目： | 广东省科技厅科技攻关基金 |
| |
| 摘 要： | 为了实现灰度图像的自动分类以及自动分割,提出了一种基于人工免疫及最优分类数的灰度图像多阈值自动分割方法.定义了灰度图像最优分类数目标函数;接着运用人工免疫算法,结合最优分类数函数对灰度图像进行自动分类,并产生最优的多阈值,从而使得图像的全自动分割成为可能.该人工免疫算法中,抗原是指最优分类数目标函数,而抗体是指最优的多阈值.通过实验证明,分类清晰,效果良好.
|
| 关 键 词： | 聚类分析 人工免疫算法 图像分割 图像分类 最优化 人工免疫 灰度图像 多阈值 自动分割 artificial immune algorithm based image segmentation 效果 验证 抗体 抗原 目标函数 结合 免疫算法 运用 分割方法 分类数 最优 |
| 文章编号： | 1000-7024（2007）01-0106-03 |
| 修稿时间： | 2005-12-15 |
Automatic multi-threshold image segmentation based on artificial immune algorithm |
| |
| LI Bin,TIAN Lian-fang,MAO Zong-yuan.Automatic multi-threshold image segmentation based on artificial immune algorithm[J].Computer Engineering and Design,2007,28(1):106-108. |
| |
| Authors: | LI Bin TIAN Lian-fang MAO Zong-yuan |
| |
| Affiliation: | College of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, China |
| |
| Abstract: | For the number of clusters is determined automatically so thata multi-thresholdimage is segmented automatically,an automatic image segmentation method based on AIA(artificial immune algorithm) and optimal number of clustering is presented.First,the objective function for the optimal number of clustering is presented.Then,an artificial immune approach is presented to generate auto-matically the number of clusters and segmentation thresholds.In this approach,the objective function is regarded as antigens,and the number of clusters and segmentation thresholds are regarded as antibodies.Experiments demonstrate the good performance of the pro-posed method. |
| |
| Keywords: | clustering analysis artificial immune algorithm image segmentation image classification optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
