• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2008, Vol. 30 ›› Issue (9): 44-46.

• 论文 • 上一篇    下一篇

基于颜色直方图熵值及分块主色的图像检索

徐果毅 朱宁波 朱晓林 卢晓阳   

  • 出版日期:2008-09-01 发布日期:2010-05-18

  • Online:2008-09-01 Published:2010-05-18

摘要:

为了克服在检索相同背景中物体颜色不同的图像时无法利用颜色特征而必须利用物体的形状特征这一缺陷,并进一步提高图像的检索效果,本文提出了一种基于颜色直方图熵值及分块主色的图像检索方法。实验结果表明,该方法不仅可以提高图像检索的查准率与查全率,而且对于检索相同背景中物体颜色不同的图像时只利用颜色特性即可达 检索目的。

关键词: 图像检索 颜色直方图 信息熵 分块主色

Abstract:

In order to overcome the defect that retrieving images of different object colors in the same background cannot use the feature of colors, but must use the feature of object shapes,and further enhance the image retrieval effect,the paper proposes a method of image retrieval based on the color histogr  m entropy value and the sub-block main color. The experimental results show that the method can not only improve the precision rate and the recall ratof image retrieval, but also retrieve the images of different object colors in the same background using only the feature of colors.

Key words: image retrieval;color histogram, information entropy, main color of image blocks