An image retrieval approach using improved color histogram based on central area

In order to overcome the defect that the conventional color histogram retrieval method is prone to lose the spatial information of colors, this paper presents an image retrieval method based on improved color histogram which uses the largest color-connected regions and its rim roughness to capture the regional traits. Besides of that, considering that main objects are concentrated on the central area, we calculate the similarity between images based on central area instead of the traditional method which take the image as a whole to reflect the human's recognition process. The experimental result on real-world image collections indicates that the proposed approach significantly improves image retrieval accuracy. 1548-7741/ Copyright © 2009 Binary Information Press.