Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (29): 98-100.

• 学术探讨 • Previous Articles     Next Articles

Image retrieval based on CIELab color space and color spatial distribution entropy

YE Guo-jun,WANG Shao-di   

  1. College of Computer,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-11 Published:2007-10-11
  • Contact: YE Guo-jun

基于CIELab颜色空间和颜色分布信息熵的图像检索

叶国军,王绍棣   

  1. 南京邮电大学 计算机学院,南京 210003
  • 通讯作者: 叶国军

Abstract: According to the color image retrieval based on the entropy feature of color,a new advanced algorithm based on CIELab color space is proposed.Because of the Uniformity of CIELab Chromaticity space which is used to differentiate colors,the color entropy feature will be more close to human vision system.In addition,a new comparison algorithm which introduces a function of the quantity of color is proposed.Experiments show that better results can be achieved.

Key words: image retrieval, CIELab color space, color spatial distribution entropy

摘要: 针对基于颜色空间信息熵的图像检索,提出了一种新的改进方案,使对颜色特征的提取建立在CIELab颜色空间的基础之上。利用CIELab的均匀颜色空间特性,来完成对颜色空间的分割,使之更符合人眼的色彩感觉特性,得到符合人眼色彩感觉的颜色空间信息熵。在图像相似性度量方面,提出了加权颜色统计函数的比较方法。经实验表明,该算法能够获得比较满意的效果。

关键词: 图像检索, CIELab颜色空间, 颜色空间信息熵