Skip to main navigation Skip to search Skip to main content

Using sharable ontology to retrieve historical images

  • Von Wun Soo*
  • , Chen Yu Lee
  • , Jaw Jium Yeh
  • , Ching Chih Chen
  • *Corresponding author for this work
  • National Tsing Hua University
  • Simmons College

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

15 Scopus citations

Abstract

We present a framework of utilizing sharable domain ontology and thesaurus to help the retrieval of historical images of the First Emperor of China's terracotta warriors and horses. Incorporating the sharable domain ontology in RDF and RDF schemas of semantic web and a thesaurus, we implement methods to allow easily annotating images into RDF instances and parsing natural language like queries into the query schema in XML format. We also implement a partial structural matching algorithm to match the query schema with images at the level of semantic schemas. Therefore the historical images can be retrieved by naïve users of domain specific history in terms of natural language like queries.

Original languageEnglish
Title of host publicationJCDL 2002
Subtitle of host publicationProceedings of the 2nd ACM/IEEE-CS Joint Conference on Digital Libraries
PublisherAssociation for Computing Machinery (ACM)
Pages197-198
Number of pages2
ISBN (Print)1581135130, 9781581135138
DOIs
StatePublished - 2002
Externally publishedYes
Event2nd ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL 2002 - Portland, OR, United States
Duration: 14 07 2002 → 18 07 2002

Publication series

NameProceedings of the ACM International Conference on Digital Libraries

Conference

Conference2nd ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL 2002
Country/TerritoryUnited States
CityPortland, OR
Period14/07/02 → 18/07/02

Keywords

  • Historical image retrieval
  • Multi-agent systems
  • RDF schemas
  • Semantic web
  • Sharable ontology
  • XML

Fingerprint

Dive into the research topics of 'Using sharable ontology to retrieve historical images'. Together they form a unique fingerprint.

Cite this