Image Retrieval based on Color Moments

Content based image retrieval (CBIR) systems are used for searching, retrieving and browsing of image databases. In this paper, we propose a color image retrieval method based on color moments. Many indexing techniques are based on global feature distributions. However, these global distributions have limited discriminating power because they are unable to capture local image information. To improve the discriminating power of color indexing techniques, we encode a minimal amount of spatial information in the index. First, an image is divided horizontally into three equal non overlapping regions. From each region in the image, we extract the first three moments (mean, variance and skewness) of the color distribution, from each color channel and store them in the index i.e., for a HSV color space, we store 27 floating point numbers per image. The similarity function which is used for retrieval is a weighted sum of the absolute differences between the corresponding moments. Our experiments demonstrate that the encoding of spatial information in the index significantly increases the discriminating power of the index compared to the color moment, based on global approach.