The goal of this research project is to design and implement a system for content-based image retrieval that can (1) provide a large variety of image-distance measures that can be used singly or in combination to satisfy a wide range of user needs and (2) provide rapid access to images, even in an extremely large database. The focus of the work is the development of a general, scalable architecture to support fast querying of very large image databases with user-specified distance measures. This includes the development of distance-measure-independent algorithms and data structures for efficient image retrieval from large databases. Methods for merging the general, distance-measure-independent algorithms with other useful techniques that may be distance measure specific, such as keyword retrieval and relational indexing, are being pursued. The problem of providing users with multiple distance measures of many different varieties is being studied. New methods for combining distance measures and a language in which users can specify their queries without detailed knowledge of the underlying metrics are being designed. A prototype system is being implemented to test the developed methods, and evaluation is being performed on both a large general image database and a smaller controlled database. The results of this research will be: (1) techniques that facilitate rapid retrieval of images by eliminating huge portions of the image database from the search, making content-based retrieval feasible on very large and growing databases; (2) new, high-level methods by which users can combine distance measures to form meaningful queries, so that content-based queries can become a standard way to query image databases; and (3) a general framework for content-based retrieval that can accommodate new distance measures as they are developed by other research efforts. The work has application to medicine, art, photography, entertainment, and advertising/marketing.
