Color image retrieval using edge-spatial feature

Color image retrieval based on histogram is analyzed and a novel method is proposed based on the image edge information. Firstly, the image edge is extracted by the use of the color vector angles because of its character which is insensitive to illumination but sensitive to hue and saturation. Then, the color vector angle histogram of the image edge is constructed to describe the image feature. With this descriptor, the color information, edge information and shape feature have been taken into account. Experimental results have shown that the proposed method not only has sound retrieval performance but also has the robustness against illumination changes, position translation, scale translation of the image content.