Abstract:Color histogram is an important technique for color image database indexing and retrieving.However,the main problem of color histogram indexing is that it does not take the spatial relationship of the colors into consideration.Previous researches show that the effectiveness of image retrieval increases when the spatial relationship of colors is considered.We use the color distribution entropy (CDE) and improved CDE (I-CDE) to describe the global spatial relationship of colors.In comparison with the spatial chromatic histogram (SCH) and geostat,which also measure the global spatial relationship of colors,the experiment results show that CDE and I-CDE give better performance than SCH and geostat.