Abstract:

With the proliferation of multimedia, the web and digital imaging, there now exists a high demand for intelligent tools for image management, most importantly indexing, search and retrieval, commonly referred to as \"query-by-image-content\". Existing systems often make use of global attributes such as overall color distributions which ignore the actual composition of the image in terms of internal structures. In this paper we present an image retrieval system predicated on the principle that it is the user who is most qualified to specify the \"content\" in an image and not the computer. Therefore, the user is asked to provide salient \"regions-of-interest\" or ROIs and specify the importance of their spatial relationships in the query image. This technique leads to acceptable retrievals (equal if not better than global-based searches) and provides an intuitive interface that is more in tune with the user\'s notion of \"content\", thus providing a more powerful image retrieval tool.