Content-based image retrieval using color histogram

This paper introduces the principles of using color histogram to match images in CBIR (content-based image retrieval). And a prototype CBIR system is designed with color matching function. A method using 2-dimensional color histogram based on hue and saturation to extract and represent color information of an image is presented. We also improve the Euclidean-distance algorithm by adding center of color to it. The experiment shows modifications made to Euclidean-distance significantly elevate the quality and efficiency of retrieval.