Heuristics for image retrieval using spatial configurations

This paper describes a strategy for content-based image retrievalvia spatial configuration of objects within an image. The proposed strategy locates "pattern" images within "text" images, where the objects in each image are specified only in terms of their pairwise spatial relati...

Full description

Bibliographic Details
Main Authors: Smyth, Bill, Lam, Chiou, Chen, X., Maxville, Valerie
Other Authors: Changming Sun
Format: Conference Paper
Published: The University of Queensland 2003
Online Access:http://hdl.handle.net/20.500.11937/13205
_version_ 1848748285462839296
author Smyth, Bill
Lam, Chiou
Chen, X.
Maxville, Valerie
author2 Changming Sun
author_facet Changming Sun
Smyth, Bill
Lam, Chiou
Chen, X.
Maxville, Valerie
author_sort Smyth, Bill
building Curtin Institutional Repository
collection Online Access
description This paper describes a strategy for content-based image retrievalvia spatial configuration of objects within an image. The proposed strategy locates "pattern" images within "text" images, where the objects in each image are specified only in terms of their pairwise spatial relationships. Thus both pattern and text are represented by square matrices whose elements are drawn from an "alphabet" of spatial relationships. A match is found when the pattern image is identified as a "substructure" of a given text image. Experimental results relating to retrieval of images with low image content are shown. The approach can be used in situations where methods involving features such as colours and texture are inappropriate. We believe that such algorithms would find application in topological/GIS applications where the aerial/satellite images are very similar in terms of low-level image content.
first_indexed 2025-11-14T07:02:37Z
format Conference Paper
id curtin-20.500.11937-13205
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:02:37Z
publishDate 2003
publisher The University of Queensland
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-132052022-09-13T04:43:08Z Heuristics for image retrieval using spatial configurations Smyth, Bill Lam, Chiou Chen, X. Maxville, Valerie Changming Sun Hugues Talbot Sbastien Ourselin Tony Adriaansen This paper describes a strategy for content-based image retrievalvia spatial configuration of objects within an image. The proposed strategy locates "pattern" images within "text" images, where the objects in each image are specified only in terms of their pairwise spatial relationships. Thus both pattern and text are represented by square matrices whose elements are drawn from an "alphabet" of spatial relationships. A match is found when the pattern image is identified as a "substructure" of a given text image. Experimental results relating to retrieval of images with low image content are shown. The approach can be used in situations where methods involving features such as colours and texture are inappropriate. We believe that such algorithms would find application in topological/GIS applications where the aerial/satellite images are very similar in terms of low-level image content. 2003 Conference Paper http://hdl.handle.net/20.500.11937/13205 The University of Queensland restricted
spellingShingle Smyth, Bill
Lam, Chiou
Chen, X.
Maxville, Valerie
Heuristics for image retrieval using spatial configurations
title Heuristics for image retrieval using spatial configurations
title_full Heuristics for image retrieval using spatial configurations
title_fullStr Heuristics for image retrieval using spatial configurations
title_full_unstemmed Heuristics for image retrieval using spatial configurations
title_short Heuristics for image retrieval using spatial configurations
title_sort heuristics for image retrieval using spatial configurations
url http://hdl.handle.net/20.500.11937/13205