PROGRESSIVE SEARCH AND RETRIEVAL IN LARGE IMAGE ARCHIVES

In this paper, we describe the architecture and implementation of a fr amework to perform content-based search of an image database, where co ntent is specified by the user at one or more of the following three a bstraction levels: pixel, feature, and semantic. This framework incorp orates a methodology that yields a computationally efficient implement ation of image-processing algorithms, thus allowing the efficient extr action and manipulation of user-specified features and content during the execution of queries. The framework is well suited for searching s cientific databases, such as satellite-image-, medical-, and seismic-d ata repositories, where the volume and diversity of the information do not allow the a priori generation of exhaustive indexes, but we have successfully demonstrated its usefulness on still-image archives.