Spatial similarity and annotation-based image retrieval system

SooCheol Lee, Een Jun Hwang

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

8 Citations (Scopus)

Abstract

Content-based image retrieval (CBIR) systems often rely on global image characteristics such as color and texture histograms, but not the spatial relationships among component objects of an image. In this paper, we describe a new image retrieval scheme where objects of interest in an image are first identified and spatial relationships among them as well as their features including semantic information are annotated to represent the image. An important and unique aspect of the system is that users are allowed to formulate a query based on both objects of an image and their spatial relationships. This could give better precision and flexibility to retrieve images from image databases. In the prototype system, semantic information of interest for objects and the spatial relationships among them are captured and represented using XML.

Original languageEnglish
Title of host publicationProceedings - 4th International Symposium on Multimedia Software Engineering, MSE 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages33-36
Number of pages4
ISBN (Print)0769518575, 9780769518572
DOIs
Publication statusPublished - 2002
Externally publishedYes
Event4th International Symposium on Multimedia Software Engineering, MSE 2002 - Newport Beach, United States
Duration: 2002 Dec 112002 Dec 13

Other

Other4th International Symposium on Multimedia Software Engineering, MSE 2002
CountryUnited States
CityNewport Beach
Period02/12/1102/12/13

Fingerprint

Image retrieval
Semantics
XML
Textures
Color

Keywords

  • Annotation
  • Image retrieval
  • Spatial relationship
  • XML

ASJC Scopus subject areas

  • Software
  • Media Technology

Cite this

Lee, S., & Hwang, E. J. (2002). Spatial similarity and annotation-based image retrieval system. In Proceedings - 4th International Symposium on Multimedia Software Engineering, MSE 2002 (pp. 33-36). [1181593] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MMSE.2002.1181593

Spatial similarity and annotation-based image retrieval system. / Lee, SooCheol; Hwang, Een Jun.

Proceedings - 4th International Symposium on Multimedia Software Engineering, MSE 2002. Institute of Electrical and Electronics Engineers Inc., 2002. p. 33-36 1181593.

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

Lee, S & Hwang, EJ 2002, Spatial similarity and annotation-based image retrieval system. in Proceedings - 4th International Symposium on Multimedia Software Engineering, MSE 2002., 1181593, Institute of Electrical and Electronics Engineers Inc., pp. 33-36, 4th International Symposium on Multimedia Software Engineering, MSE 2002, Newport Beach, United States, 02/12/11. https://doi.org/10.1109/MMSE.2002.1181593
Lee S, Hwang EJ. Spatial similarity and annotation-based image retrieval system. In Proceedings - 4th International Symposium on Multimedia Software Engineering, MSE 2002. Institute of Electrical and Electronics Engineers Inc. 2002. p. 33-36. 1181593 https://doi.org/10.1109/MMSE.2002.1181593
Lee, SooCheol ; Hwang, Een Jun. / Spatial similarity and annotation-based image retrieval system. Proceedings - 4th International Symposium on Multimedia Software Engineering, MSE 2002. Institute of Electrical and Electronics Engineers Inc., 2002. pp. 33-36
@inproceedings{0fd650e4209041848cf1a0aa2aa3d388,
title = "Spatial similarity and annotation-based image retrieval system",
abstract = "Content-based image retrieval (CBIR) systems often rely on global image characteristics such as color and texture histograms, but not the spatial relationships among component objects of an image. In this paper, we describe a new image retrieval scheme where objects of interest in an image are first identified and spatial relationships among them as well as their features including semantic information are annotated to represent the image. An important and unique aspect of the system is that users are allowed to formulate a query based on both objects of an image and their spatial relationships. This could give better precision and flexibility to retrieve images from image databases. In the prototype system, semantic information of interest for objects and the spatial relationships among them are captured and represented using XML.",
keywords = "Annotation, Image retrieval, Spatial relationship, XML",
author = "SooCheol Lee and Hwang, {Een Jun}",
year = "2002",
doi = "10.1109/MMSE.2002.1181593",
language = "English",
isbn = "0769518575",
pages = "33--36",
booktitle = "Proceedings - 4th International Symposium on Multimedia Software Engineering, MSE 2002",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Spatial similarity and annotation-based image retrieval system

AU - Lee, SooCheol

AU - Hwang, Een Jun

PY - 2002

Y1 - 2002

N2 - Content-based image retrieval (CBIR) systems often rely on global image characteristics such as color and texture histograms, but not the spatial relationships among component objects of an image. In this paper, we describe a new image retrieval scheme where objects of interest in an image are first identified and spatial relationships among them as well as their features including semantic information are annotated to represent the image. An important and unique aspect of the system is that users are allowed to formulate a query based on both objects of an image and their spatial relationships. This could give better precision and flexibility to retrieve images from image databases. In the prototype system, semantic information of interest for objects and the spatial relationships among them are captured and represented using XML.

AB - Content-based image retrieval (CBIR) systems often rely on global image characteristics such as color and texture histograms, but not the spatial relationships among component objects of an image. In this paper, we describe a new image retrieval scheme where objects of interest in an image are first identified and spatial relationships among them as well as their features including semantic information are annotated to represent the image. An important and unique aspect of the system is that users are allowed to formulate a query based on both objects of an image and their spatial relationships. This could give better precision and flexibility to retrieve images from image databases. In the prototype system, semantic information of interest for objects and the spatial relationships among them are captured and represented using XML.

KW - Annotation

KW - Image retrieval

KW - Spatial relationship

KW - XML

UR - http://www.scopus.com/inward/record.url?scp=33645655042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645655042&partnerID=8YFLogxK

U2 - 10.1109/MMSE.2002.1181593

DO - 10.1109/MMSE.2002.1181593

M3 - Conference contribution

SN - 0769518575

SN - 9780769518572

SP - 33

EP - 36

BT - Proceedings - 4th International Symposium on Multimedia Software Engineering, MSE 2002

PB - Institute of Electrical and Electronics Engineers Inc.

ER -