| 基于最优分类数及遗传算法的灰度图像多阈值自动分割法 |
| |
| 引用本文： | 郑成勇,李红,高景丽.基于最优分类数及遗传算法的灰度图像多阈值自动分割法[J].计算机工程与应用,2003,39(23):79-80,83. |
| |
| 作者姓名： | 郑成勇 李红 高景丽 |
| |
| 作者单位： | 华中科技大学数学系,武汉,430074 |
| |
| 摘 要： | 如何确定分类数是模式识别和图像分割中常要面对的难题。文献犤1犦提出了一种基于阴阳机制确定最优分类数的模式聚类方法。该文在文献犤1犦的基础上,导出了一个新的用于评价灰度图像多阈值分割的评价标准,并结合遗传算法,提出了一种用于灰度图像的多阈值自动分割方案。试验表明,该法具有较强的鲁棒性、适用性、非监督性。
|
| 关 键 词： | 图像分割 遗传算法 聚类数选择标准 |
| 文章编号： | 1002-8331-(2003)23-0079-02 |
Automatic Multi Threshold Image Segmentation Based on Genetic and Optimal Number of Cluster |
| |
| Zheng Chengyong Li,Hong Gao Jingli.Automatic Multi Threshold Image Segmentation Based on Genetic and Optimal Number of Cluster[J].Computer Engineering and Applications,2003,39(23):79-80,83. |
| |
| Authors: | Zheng Chengyong Li Hong Gao Jingli |
| |
| Abstract: | How to determine the number of clusters is an open problem that is faced by pattern recognition and image segmentation.The Bayesian YING-YANG learning theory and system proposed byprovides people the model selection criteria for selecting the number of clusters in the clustering analysis.Based onand the genetic algorithm,this paper proposes a novel scheme for gray image segmentation.Experimental results show the effectiveness of this method. |
| |
| Keywords: | Image Segmentation Genetic Algorithm Criteria for Selecting the Number of Clusters |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
