计算机与现代化 ›› 2009, Vol. 1 ›› Issue (10): 88-4.doi: 10.3969/j.issn.1006-2475.2009.10.025

• 图像处理 • 上一篇    下一篇

聚类分析在非监督图像分类中的应用研究

孟海东1,郝永宽2,王淑玲2   

  1. 1.内蒙古科技大学资源与安全工程学院,内蒙古 包头 014010;2.内蒙古科技大学信息工程学院,内蒙古 包头 014010
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-10-15 发布日期:2009-10-15

Application Research on Clustering Analysis in Unsupervised Image Classification

MENG Hai-dong1,HAO Yong-kuan2,WANG Shu-ling2   

  1. 1.School of Resource and Safety Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, China; 2.School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-10-15 Published:2009-10-15

摘要:

为了提高聚类分析在非监督计算机图像分类中的应用效果,将设计并实现的基于密度和自适应密度可达聚类分析算法应用于图像分类。通过与K-means和层次聚类对图像分类效果的实验对比,证明了基于密度和自适应密度可达聚类分析算法在非监督计算机图像分类中具有良好的应用效果。

关键词: 非监督分类, 图像分类, 聚类算法

Abstract:

In order to improve the application effectiveness of clustering analysis in unsupervised image classification, Clustering Algorithm based on Density and adaptive Densityreachable (CADD), which is designed and applied to image classification. Compared with the classifying results of Kmeans and hierarchical method, it is evident that CADD has good effects in unsupervised image classification.

Key words: unsupervised classification, image classification, clustering algorithm