Regions-of-interest and spatial layout for content-based image retrieval

To date most "content-based image retrieval" (CBIR) techniques rely on glob al attributes such as color or texture histograms which tend to ignore the spatial composition of the image. In this paper, we present an alternative image retrieval system based on the principle that it is the user who is mo st qualified to specify the query "content" and not the computer. With our system, the user can select multiple "regions-of-interest" and can specify the relevance of their spatial layout in the retrieval process. We also der ive similarity bounds on histogram distances for pruning the database searc h. This experimental system was found to be superior to global indexing tec hniques as measured by statistical sampling of multiple users' "satisfactio n" ratings.