期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：1998
卷号：XXXII Part 4
出版社：Copernicus Publications
摘要：The intelligent retrieval of images from large databases is receiving increased attention in the computer visioncommunity. In this paper we address this problem considering the particularities of image databases encountered intypical topographic applications. Specifically, we present the development of a spatial data management system whichenables the use of sketch-based queries for the content-based retrieval of digital images from topographic databases.We discuss our overall strategy and present some relevant algorithmic and implementation aspects, as well asassociated database design issues. The query input are user-provided sketches of the shape and spatial configuration ofthe object (or objects) which should appear in the images to be retrieved. The objective of the database search is toretrieve images which contain a configuration of objects sufficiently similar to the one specified in the query. The resultsare ranked according to statistical scores and the user can subsequently narrow or broaden his/her search according tothe previously obtained results and the purpose of the search. Our approach combines the design of an integrateddatabase with the development of the necessary matching tools. Our matching tool specifically is inspired by leastsquaresmatching, and represents an extension of lsm to function with a variety of raster representations. The potentialto eventually handle digital maps and general GIS datasets, in addition to images, makes this a solid step towards theintegration of GIS and image databases
关键词：Image Retrieval; Spatial Information Management Systems; Shape Queries; Integrated Environments
