An Image Retrieval Method Based on Color and Texture Features

作     者：LIU Wei-jie HU Jian-ling XU Cheng-liang 

作者机构：Inst. of Image Communication & Information ProcessingShanghai Jiaotong Univ.Shanghai 200030China 

出 版 物：《Journal of Shanghai Jiaotong University(Science)》 (JOURNAL OF SHANGHAI JIAOTONG UNIVERSITY(SCIENCE))

年 卷 期：2006年第000卷第4期

页      面：537-542页

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 

主　　题：image retrieval color histogram earth Mover's distance(EMD) texture spectrum 

摘      要：The technique of image retrieval is widely used in science experiment, military affairs, public security,advertisement, family entertainment, library and so on. The existing algorithms are mostly based on the characteristics of color, texture, shape and space relationship. This paper introduced an image retrieval algorithm, which is based on the matching of weighted EMD(Earth Mover s Distance) distance and texture distance. EMD distance is the distance between the histograms of two images in HSV(Hue, Saturation, Value) color space, and texture distance is the L1 distance between the texture spectra of two images. The experimental results show that the retrieval rate can be increased obviously by using the proposed algorithm.