An environment for content-based image retrieval from large spatial databases

In this paper, we address the problem of content-based image retrieval usin g queries on shape and topology. We focus on the particularities of image d atabases encountered in typical topographic applications and present the de velopment of a spatial data management system that enables such queries. Th e query requires user-provided sketches of the shape and spatial configurat ion of the object (or objects) which should appear in the images to be retr ieved. The objective of the search is to retrieve images that contain a con figuration of objects sufficiently similar to the one specified in the quer y. Our approach combines the design of an integrated database with the deve lopment of a feature library and the necessary matching tools. In this pape r, we present our overall scheme, introduce some individual database compon ents, and provide some implementation results. (C) 1999 Elsevier Science B. V. All rights reserved.