An intelligent annotation-based image retrieval system based on RDF descriptions

Hua Chen, Antoine Trouve, Kazuaki J. Murakami, Akira Fukuda

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, we aim at improving text-based image search using Semantic Web technologies. We introduce our notions of concept and instance in order to better express the semantics of images, and present an intelligent annotation-based image retrieval system. We test our approach on the Flickr8k dataset. From the provided captions, we generate annotations at three levels (sentence, concept and instance). These annotations are stored as RDF triples and can be queried to find images. The experimental results show that using concepts and instances to annotate images flexibly can improve the intelligence of the image retrieval system: (1) with annotations at concept level, it enables to create semantic links between concepts and then addresses many challenges, such as the problems of synonyms and homonyms; (2) with annotations at instance level, it can count things (e.g., “two people”, “three animals”) or identify a same concept.

Original languageEnglish
Pages (from-to)537-550
Number of pages14
JournalComputers and Electrical Engineering
Volume58
DOIs
Publication statusPublished - Feb 1 2017

Fingerprint

Image retrieval
Semantics
Semantic Web
Animals

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

An intelligent annotation-based image retrieval system based on RDF descriptions. / Chen, Hua; Trouve, Antoine; Murakami, Kazuaki J.; Fukuda, Akira.

In: Computers and Electrical Engineering, Vol. 58, 01.02.2017, p. 537-550.

Research output: Contribution to journalArticle

Chen, Hua ; Trouve, Antoine ; Murakami, Kazuaki J. ; Fukuda, Akira. / An intelligent annotation-based image retrieval system based on RDF descriptions. In: Computers and Electrical Engineering. 2017 ; Vol. 58. pp. 537-550.
@article{1b1cd7ff7376483d9ce88f71a34664cc,
title = "An intelligent annotation-based image retrieval system based on RDF descriptions",
abstract = "In this paper, we aim at improving text-based image search using Semantic Web technologies. We introduce our notions of concept and instance in order to better express the semantics of images, and present an intelligent annotation-based image retrieval system. We test our approach on the Flickr8k dataset. From the provided captions, we generate annotations at three levels (sentence, concept and instance). These annotations are stored as RDF triples and can be queried to find images. The experimental results show that using concepts and instances to annotate images flexibly can improve the intelligence of the image retrieval system: (1) with annotations at concept level, it enables to create semantic links between concepts and then addresses many challenges, such as the problems of synonyms and homonyms; (2) with annotations at instance level, it can count things (e.g., “two people”, “three animals”) or identify a same concept.",
author = "Hua Chen and Antoine Trouve and Murakami, {Kazuaki J.} and Akira Fukuda",
year = "2017",
month = "2",
day = "1",
doi = "10.1016/j.compeleceng.2016.09.031",
language = "English",
volume = "58",
pages = "537--550",
journal = "Computers and Electrical Engineering",
issn = "0045-7906",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - An intelligent annotation-based image retrieval system based on RDF descriptions

AU - Chen, Hua

AU - Trouve, Antoine

AU - Murakami, Kazuaki J.

AU - Fukuda, Akira

PY - 2017/2/1

Y1 - 2017/2/1

N2 - In this paper, we aim at improving text-based image search using Semantic Web technologies. We introduce our notions of concept and instance in order to better express the semantics of images, and present an intelligent annotation-based image retrieval system. We test our approach on the Flickr8k dataset. From the provided captions, we generate annotations at three levels (sentence, concept and instance). These annotations are stored as RDF triples and can be queried to find images. The experimental results show that using concepts and instances to annotate images flexibly can improve the intelligence of the image retrieval system: (1) with annotations at concept level, it enables to create semantic links between concepts and then addresses many challenges, such as the problems of synonyms and homonyms; (2) with annotations at instance level, it can count things (e.g., “two people”, “three animals”) or identify a same concept.

AB - In this paper, we aim at improving text-based image search using Semantic Web technologies. We introduce our notions of concept and instance in order to better express the semantics of images, and present an intelligent annotation-based image retrieval system. We test our approach on the Flickr8k dataset. From the provided captions, we generate annotations at three levels (sentence, concept and instance). These annotations are stored as RDF triples and can be queried to find images. The experimental results show that using concepts and instances to annotate images flexibly can improve the intelligence of the image retrieval system: (1) with annotations at concept level, it enables to create semantic links between concepts and then addresses many challenges, such as the problems of synonyms and homonyms; (2) with annotations at instance level, it can count things (e.g., “two people”, “three animals”) or identify a same concept.

UR - http://www.scopus.com/inward/record.url?scp=85002002536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85002002536&partnerID=8YFLogxK

U2 - 10.1016/j.compeleceng.2016.09.031

DO - 10.1016/j.compeleceng.2016.09.031

M3 - Article

AN - SCOPUS:85002002536

VL - 58

SP - 537

EP - 550

JO - Computers and Electrical Engineering

JF - Computers and Electrical Engineering

SN - 0045-7906

ER -