Semantically indexed and searched of digital images using lexical ontologies and named entity recognition

Datul Aida Ali, Shahrul Azman Mohd Noah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Using low-level features to support semantic search of images is a difficult task. As a result, textual content is used to provide semantic description or annotation of images. Such textual description of what we may call as 'surrounding text' is a value added features available in most web images particularly on-line newspaper images. Most search engines used them as a feature to provide textual meaning of images. Relying on surrounding text alone, however, unable to provide support for semantic search that go beyond indexed terms. Lexical resources and ontology are potential sources to enhance searching for images. This paper discusses the use of WordNet and ConceptNet to enhance searching for on-line newspaper images. This is further improved with named entity recognition (NER) technique to annotate important entities such as name if a person, location and organization among image searchers. Results show that our semantic search approaches outperform the normal approach for searching images.

Original languageEnglish
Title of host publicationProceedings 2010 International Symposium on Information Technology - System Development and Application and Knowledge Society, ITSim'10
Pages1308-1314
Number of pages7
Volume3
DOIs
Publication statusPublished - 2010
Event2010 International Symposium on Information Technology, ITSim'10 - Kuala Lumpur
Duration: 15 Jun 201017 Jun 2010

Other

Other2010 International Symposium on Information Technology, ITSim'10
CityKuala Lumpur
Period15/6/1017/6/10

Fingerprint

Ontology
Semantics
Search engines
World Wide Web

Keywords

  • Component
  • Information retrieval
  • Natural language processing
  • Semantic search

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Ali, D. A., & Mohd Noah, S. A. (2010). Semantically indexed and searched of digital images using lexical ontologies and named entity recognition. In Proceedings 2010 International Symposium on Information Technology - System Development and Application and Knowledge Society, ITSim'10 (Vol. 3, pp. 1308-1314). [5561455] https://doi.org/10.1109/ITSIM.2010.5561455

Semantically indexed and searched of digital images using lexical ontologies and named entity recognition. / Ali, Datul Aida; Mohd Noah, Shahrul Azman.

Proceedings 2010 International Symposium on Information Technology - System Development and Application and Knowledge Society, ITSim'10. Vol. 3 2010. p. 1308-1314 5561455.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ali, DA & Mohd Noah, SA 2010, Semantically indexed and searched of digital images using lexical ontologies and named entity recognition. in Proceedings 2010 International Symposium on Information Technology - System Development and Application and Knowledge Society, ITSim'10. vol. 3, 5561455, pp. 1308-1314, 2010 International Symposium on Information Technology, ITSim'10, Kuala Lumpur, 15/6/10. https://doi.org/10.1109/ITSIM.2010.5561455
Ali DA, Mohd Noah SA. Semantically indexed and searched of digital images using lexical ontologies and named entity recognition. In Proceedings 2010 International Symposium on Information Technology - System Development and Application and Knowledge Society, ITSim'10. Vol. 3. 2010. p. 1308-1314. 5561455 https://doi.org/10.1109/ITSIM.2010.5561455
Ali, Datul Aida ; Mohd Noah, Shahrul Azman. / Semantically indexed and searched of digital images using lexical ontologies and named entity recognition. Proceedings 2010 International Symposium on Information Technology - System Development and Application and Knowledge Society, ITSim'10. Vol. 3 2010. pp. 1308-1314
@inproceedings{702a995cfd194b49b08b8a614733564a,
title = "Semantically indexed and searched of digital images using lexical ontologies and named entity recognition",
abstract = "Using low-level features to support semantic search of images is a difficult task. As a result, textual content is used to provide semantic description or annotation of images. Such textual description of what we may call as 'surrounding text' is a value added features available in most web images particularly on-line newspaper images. Most search engines used them as a feature to provide textual meaning of images. Relying on surrounding text alone, however, unable to provide support for semantic search that go beyond indexed terms. Lexical resources and ontology are potential sources to enhance searching for images. This paper discusses the use of WordNet and ConceptNet to enhance searching for on-line newspaper images. This is further improved with named entity recognition (NER) technique to annotate important entities such as name if a person, location and organization among image searchers. Results show that our semantic search approaches outperform the normal approach for searching images.",
keywords = "Component, Information retrieval, Natural language processing, Semantic search",
author = "Ali, {Datul Aida} and {Mohd Noah}, {Shahrul Azman}",
year = "2010",
doi = "10.1109/ITSIM.2010.5561455",
language = "English",
isbn = "9781424467181",
volume = "3",
pages = "1308--1314",
booktitle = "Proceedings 2010 International Symposium on Information Technology - System Development and Application and Knowledge Society, ITSim'10",

}

TY - GEN

T1 - Semantically indexed and searched of digital images using lexical ontologies and named entity recognition

AU - Ali, Datul Aida

AU - Mohd Noah, Shahrul Azman

PY - 2010

Y1 - 2010

N2 - Using low-level features to support semantic search of images is a difficult task. As a result, textual content is used to provide semantic description or annotation of images. Such textual description of what we may call as 'surrounding text' is a value added features available in most web images particularly on-line newspaper images. Most search engines used them as a feature to provide textual meaning of images. Relying on surrounding text alone, however, unable to provide support for semantic search that go beyond indexed terms. Lexical resources and ontology are potential sources to enhance searching for images. This paper discusses the use of WordNet and ConceptNet to enhance searching for on-line newspaper images. This is further improved with named entity recognition (NER) technique to annotate important entities such as name if a person, location and organization among image searchers. Results show that our semantic search approaches outperform the normal approach for searching images.

AB - Using low-level features to support semantic search of images is a difficult task. As a result, textual content is used to provide semantic description or annotation of images. Such textual description of what we may call as 'surrounding text' is a value added features available in most web images particularly on-line newspaper images. Most search engines used them as a feature to provide textual meaning of images. Relying on surrounding text alone, however, unable to provide support for semantic search that go beyond indexed terms. Lexical resources and ontology are potential sources to enhance searching for images. This paper discusses the use of WordNet and ConceptNet to enhance searching for on-line newspaper images. This is further improved with named entity recognition (NER) technique to annotate important entities such as name if a person, location and organization among image searchers. Results show that our semantic search approaches outperform the normal approach for searching images.

KW - Component

KW - Information retrieval

KW - Natural language processing

KW - Semantic search

UR - http://www.scopus.com/inward/record.url?scp=78049360061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049360061&partnerID=8YFLogxK

U2 - 10.1109/ITSIM.2010.5561455

DO - 10.1109/ITSIM.2010.5561455

M3 - Conference contribution

AN - SCOPUS:78049360061

SN - 9781424467181

VL - 3

SP - 1308

EP - 1314

BT - Proceedings 2010 International Symposium on Information Technology - System Development and Application and Knowledge Society, ITSim'10

ER -