Research on integrating spatial information into content-based image retrieval is aimed at solving the problem caused by global feature based algorithm.Most systems derive the spatial information from image segmentation.However

the description of images based on one-level description (OLD) and the inevitable inaccuracy of segmentation results limit the performance.The proposed two-level description (TLD) describes images by a rough description and a detailed description to avoid improper spatial constrain caused by OLD.Similarity measurement based on unbalanced region matching (URM) is introduced in taking the advantage of TLD to reduce the influence of inaccurate segmentation.The performance of the system is illustrated by experimental results with 700 query images randomly selected from a database of 7000 general-purpose images.