Hierarchical image modeling for object-based media retrieval

Wen Syan Li, Kasim Candan, Kyoji Hirata, Yoshinori Hara

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Images are more structurally complex than the data stored in the traditional DBMSs. Many systems perform media retrieval based on image feature matching; the fact that images have structures is ignored. On the other hand, we view images as compound objects containing many component objects. Each component object corresponds to a region(s) that is a visually and semantically meaningful entity (e.g. car, man, etc.). As images/objects truly have hierarchical structures and have both visual and semantics properties, we argue that image retrieval using either semantics and image matching alone is insufficient. In this paper, we introduce a hierarchical structure for image modeling to support image retrieval using combinations of semantic expressions and visual examples at both the whole image and object levels. We give formal definitions of a multimedia query language and a system implementation based on this image modeling. We also address associated query processing issues and discuss the portability and extendibility of our approach.

Original languageEnglish (US)
Pages (from-to)139-176
Number of pages38
JournalData and Knowledge Engineering
Volume27
Issue number2
StatePublished - Sep 1998
Externally publishedYes

Fingerprint

Semantics
Image retrieval
Image matching
Query languages
Query processing
Railroad cars
Modeling

Keywords

  • Hierarchical structure
  • Image databases
  • Image modeling
  • Multimedia query language
  • Object-based image retrieval
  • SQL3

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Hierarchical image modeling for object-based media retrieval. / Li, Wen Syan; Candan, Kasim; Hirata, Kyoji; Hara, Yoshinori.

In: Data and Knowledge Engineering, Vol. 27, No. 2, 09.1998, p. 139-176.

Research output: Contribution to journalArticle

Li, WS, Candan, K, Hirata, K & Hara, Y 1998, 'Hierarchical image modeling for object-based media retrieval', Data and Knowledge Engineering, vol. 27, no. 2, pp. 139-176.
Li, Wen Syan ; Candan, Kasim ; Hirata, Kyoji ; Hara, Yoshinori. / Hierarchical image modeling for object-based media retrieval. In: Data and Knowledge Engineering. 1998 ; Vol. 27, No. 2. pp. 139-176.
@article{eff4ddcade95477093c77a026bb4bbc4,
title = "Hierarchical image modeling for object-based media retrieval",
abstract = "Images are more structurally complex than the data stored in the traditional DBMSs. Many systems perform media retrieval based on image feature matching; the fact that images have structures is ignored. On the other hand, we view images as compound objects containing many component objects. Each component object corresponds to a region(s) that is a visually and semantically meaningful entity (e.g. car, man, etc.). As images/objects truly have hierarchical structures and have both visual and semantics properties, we argue that image retrieval using either semantics and image matching alone is insufficient. In this paper, we introduce a hierarchical structure for image modeling to support image retrieval using combinations of semantic expressions and visual examples at both the whole image and object levels. We give formal definitions of a multimedia query language and a system implementation based on this image modeling. We also address associated query processing issues and discuss the portability and extendibility of our approach.",
keywords = "Hierarchical structure, Image databases, Image modeling, Multimedia query language, Object-based image retrieval, SQL3",
author = "Li, {Wen Syan} and Kasim Candan and Kyoji Hirata and Yoshinori Hara",
year = "1998",
month = "9",
language = "English (US)",
volume = "27",
pages = "139--176",
journal = "Data and Knowledge Engineering",
issn = "0169-023X",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Hierarchical image modeling for object-based media retrieval

AU - Li, Wen Syan

AU - Candan, Kasim

AU - Hirata, Kyoji

AU - Hara, Yoshinori

PY - 1998/9

Y1 - 1998/9

N2 - Images are more structurally complex than the data stored in the traditional DBMSs. Many systems perform media retrieval based on image feature matching; the fact that images have structures is ignored. On the other hand, we view images as compound objects containing many component objects. Each component object corresponds to a region(s) that is a visually and semantically meaningful entity (e.g. car, man, etc.). As images/objects truly have hierarchical structures and have both visual and semantics properties, we argue that image retrieval using either semantics and image matching alone is insufficient. In this paper, we introduce a hierarchical structure for image modeling to support image retrieval using combinations of semantic expressions and visual examples at both the whole image and object levels. We give formal definitions of a multimedia query language and a system implementation based on this image modeling. We also address associated query processing issues and discuss the portability and extendibility of our approach.

AB - Images are more structurally complex than the data stored in the traditional DBMSs. Many systems perform media retrieval based on image feature matching; the fact that images have structures is ignored. On the other hand, we view images as compound objects containing many component objects. Each component object corresponds to a region(s) that is a visually and semantically meaningful entity (e.g. car, man, etc.). As images/objects truly have hierarchical structures and have both visual and semantics properties, we argue that image retrieval using either semantics and image matching alone is insufficient. In this paper, we introduce a hierarchical structure for image modeling to support image retrieval using combinations of semantic expressions and visual examples at both the whole image and object levels. We give formal definitions of a multimedia query language and a system implementation based on this image modeling. We also address associated query processing issues and discuss the portability and extendibility of our approach.

KW - Hierarchical structure

KW - Image databases

KW - Image modeling

KW - Multimedia query language

KW - Object-based image retrieval

KW - SQL3

UR - http://www.scopus.com/inward/record.url?scp=0042355882&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0042355882&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0042355882

VL - 27

SP - 139

EP - 176

JO - Data and Knowledge Engineering

JF - Data and Knowledge Engineering

SN - 0169-023X

IS - 2

ER -