A color image retrieval method based on regional color moment and wavelet-based features

This paper proposes three new image features the regional color moment feature (RCM), the wavelet-based feature, and the RCM-wavelet feature, which are useful for retrieving color images from a color image database. The RCM feature characterizes the color-spatial information of images. The wavelet-based feature can describe not only the local and global color variances of pixels, but also some geographic shapes of objects in an image. However, the two features above can only depict the content of images in different ways. Thus, this paper presents another feature, RCM-wavelet, which integrates both features above to raise the quality of similarity measure. The experimental results demonstrate that the image retrieval method using on the RCM-wavelet feature gives a quite impressive performance.