Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (20): 40-42.

• 学术探讨 • Previous Articles     Next Articles

CBIR method based on color co-occurrence matrix

YANG Zhen-ya1,YANG Zhen-dong2,WANG Yong3,WANG Cheng-dao1   

  1. 1.College of Information,East China Normal University,Shanghai 200062,China
    2.College of Electrical and Power Engineering,Taiyuan University of Technology,Taiyuan 030024,China
    3.Department of Computer Science,Fudan University,Shanghai 200433,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-07-11 Published:2007-07-11
  • Contact: YANG Zhen-ya


杨振亚1,杨振东2,王 勇3,王成道1   

  1. 1.华东师范大学 信息学院 电子系,上海 200062
    2.太原理工大学 电气与动力工程学院,太原 030024
    3.复旦大学 计算机科学系,上海 200433
  • 通讯作者: 杨振亚

Abstract: In this paper,the methods for CBIR is based on color co-occurrence matrix—a new conception which proposed on the basis of grey level co-occurrence matrix.From the color co-occurrence matrix we can extracte both color and texture features and carry out some combined-features retrieval experiments using real-color image database.The experiments results show that the retrieval results of the methods fits closely with human perception.

Key words: Content Based Image Retrieval(CBIR), color, texture, grey level co-occurrence matrix, color co-occurrence matrix

摘要: 介绍了一种基于色彩共生矩阵提取颜色-纹理特征的图像检索方法。在灰度共生矩阵方法的基础上,发展出色彩共生矩阵方法,解决了灰度共生矩阵方法不能有效处理真彩色图像的缺陷,并从色彩共生矩阵中提取颜色和纹理特征用于图像检索。该方法易于实现、特征库简洁高效,且具有较好的检索效果。

关键词: 基于内容的图像检索, 颜色, 纹理, 灰度共生矩阵, 色彩共生矩阵