An Image Retrieval Method Based on Spatial Features of Colors

This paper presents a method for expressing color features of images through color hue histograms, according to the distribution characteristics of image color space. In this method, the spatial features of colors are described in terms of three independent components of the HSV color space, with rotation, scaling and translation invariant features. Tests have proved that favorable retrieval effects were achieved with this method in similarity retrieval of color images, and the defect that color histograms and color moment methods are not accurate enough to express the spatial positions of image colors was well overcome.