Improving the performance of multi-modality ontology image retrieval system using DBpedia

Image Retrieval System (IRS) is commonly based on searching keywords in the surrounding text of images by employing content-independent metadata, or data that is not directly concerned with image content. Content Based Image Retrieval (CBIR) focuses on image features, as it extracts image featur...

Full description

Bibliographic Details
Main Authors:	Mohd Khalid, Yanti Idaya Aspura, Mohd Noah, Shahrul Azman
Format:	Conference or Workshop Item
Language:	English
Published:	2013
Subjects:	T Technology (General)
Online Access:	http://irep.iium.edu.my/39063/ http://irep.iium.edu.my/39063/ http://irep.iium.edu.my/39063/1/1973-7276-2-PB.pdf

id	iium-39063
recordtype	eprints
spelling	iium-390632015-01-08T03:51:36Z http://irep.iium.edu.my/39063/ Improving the performance of multi-modality ontology image retrieval system using DBpedia Mohd Khalid, Yanti Idaya Aspura Mohd Noah, Shahrul Azman T Technology (General) Image Retrieval System (IRS) is commonly based on searching keywords in the surrounding text of images by employing content-independent metadata, or data that is not directly concerned with image content. Content Based Image Retrieval (CBIR) focuses on image features, as it extracts image features such as dominant color, color histogram, texture, and object shape. The main problem with CBIR is the semantic gap between low-level image features and high-level human-understandable concepts. There is a lack of agreement between information that is extracted from visual data and the text description. Ontologies are at the heart of all Semantic Web applications, representing domain concepts and relations in the form of a semantic network. In this study, we applied ontology to bridge the semantic gap by developing a prototype multi-modality ontology IRS based on sports news and by integrating it with DBpedia to enrich the knowledge base while overcoming the problem of semantic heterogeneity. We evaluate our approach using precision and recall and compare this approach with single modality ontology. The results show that multi-modality ontology IRS give high precision (P) and recall (R) compared to visual-based ontology and keyword-based ontology. 2013-08-13 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/39063/1/1973-7276-2-PB.pdf Mohd Khalid, Yanti Idaya Aspura and Mohd Noah, Shahrul Azman (2013) Improving the performance of multi-modality ontology image retrieval system using DBpedia. In: 3rd World Conference on Information Technology (WCIT-2012), 14th-16th November 2012, Spain. http://www.world-education-center.org/index.php/P-ITCS/article/viewArticle/1973
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	T Technology (General)
spellingShingle	T Technology (General) Mohd Khalid, Yanti Idaya Aspura Mohd Noah, Shahrul Azman Improving the performance of multi-modality ontology image retrieval system using DBpedia
description	Image Retrieval System (IRS) is commonly based on searching keywords in the surrounding text of images by employing content-independent metadata, or data that is not directly concerned with image content. Content Based Image Retrieval (CBIR) focuses on image features, as it extracts image features such as dominant color, color histogram, texture, and object shape. The main problem with CBIR is the semantic gap between low-level image features and high-level human-understandable concepts. There is a lack of agreement between information that is extracted from visual data and the text description. Ontologies are at the heart of all Semantic Web applications, representing domain concepts and relations in the form of a semantic network. In this study, we applied ontology to bridge the semantic gap by developing a prototype multi-modality ontology IRS based on sports news and by integrating it with DBpedia to enrich the knowledge base while overcoming the problem of semantic heterogeneity. We evaluate our approach using precision and recall and compare this approach with single modality ontology. The results show that multi-modality ontology IRS give high precision (P) and recall (R) compared to visual-based ontology and keyword-based ontology.
format	Conference or Workshop Item
author	Mohd Khalid, Yanti Idaya Aspura Mohd Noah, Shahrul Azman
author_facet	Mohd Khalid, Yanti Idaya Aspura Mohd Noah, Shahrul Azman
author_sort	Mohd Khalid, Yanti Idaya Aspura
title	Improving the performance of multi-modality ontology image retrieval system using DBpedia
title_short	Improving the performance of multi-modality ontology image retrieval system using DBpedia
title_full	Improving the performance of multi-modality ontology image retrieval system using DBpedia
title_fullStr	Improving the performance of multi-modality ontology image retrieval system using DBpedia
title_full_unstemmed	Improving the performance of multi-modality ontology image retrieval system using DBpedia
title_sort	improving the performance of multi-modality ontology image retrieval system using dbpedia
publishDate	2013
url	http://irep.iium.edu.my/39063/ http://irep.iium.edu.my/39063/ http://irep.iium.edu.my/39063/1/1973-7276-2-PB.pdf
first_indexed	2023-09-18T20:56:06Z
last_indexed	2023-09-18T20:56:06Z
_version_	1777410314781851648

Improving the performance of multi-modality ontology image retrieval system using DBpedia

Similar Items