Semantics-sensitive retrieval for digital picture libraries

James Ze Wang, Desmond Chan, Jia Li, Gio Wiederhold

Research output: Contribution to journalReview article

18 Citations (Scopus)

Abstract

We present SIMPLIcity (Semantics-sensitive Integrated Matching for Picture LIbraries), an image database retrieval system, which uses high-level semantics classification and integrated region matching based upon image segmentation. The SIMPLIcity system represents an image by a set of regions, roughly corresponding to objects, which are characterized by color, texture, shape, and location. Based on segmented regions, the system classifies images into categories which are intended to distinguish semantically meaningful differences. These high-level categories, such as textured-nontextured, indoor-outdoor, objectionable-benign, graph-photograph, enhance retrieval by narrowing down the searching range in a database and permitting semantically adaptive searching methods.

Original languageEnglish (US)
Pages (from-to)60-72
Number of pages13
JournalD-Lib Magazine
Volume5
Issue number11
DOIs
StatePublished - Nov 1 1999

Fingerprint

semantics
segmentation

All Science Journal Classification (ASJC) codes

  • Library and Information Sciences

Cite this

Wang, James Ze ; Chan, Desmond ; Li, Jia ; Wiederhold, Gio. / Semantics-sensitive retrieval for digital picture libraries. In: D-Lib Magazine. 1999 ; Vol. 5, No. 11. pp. 60-72.
@article{1e5510d6e1b14c698578f32a0c660192,
title = "Semantics-sensitive retrieval for digital picture libraries",
abstract = "We present SIMPLIcity (Semantics-sensitive Integrated Matching for Picture LIbraries), an image database retrieval system, which uses high-level semantics classification and integrated region matching based upon image segmentation. The SIMPLIcity system represents an image by a set of regions, roughly corresponding to objects, which are characterized by color, texture, shape, and location. Based on segmented regions, the system classifies images into categories which are intended to distinguish semantically meaningful differences. These high-level categories, such as textured-nontextured, indoor-outdoor, objectionable-benign, graph-photograph, enhance retrieval by narrowing down the searching range in a database and permitting semantically adaptive searching methods.",
author = "Wang, {James Ze} and Desmond Chan and Jia Li and Gio Wiederhold",
year = "1999",
month = "11",
day = "1",
doi = "10.1045/november99-wang",
language = "English (US)",
volume = "5",
pages = "60--72",
journal = "D-Lib Magazine",
issn = "1082-9873",
publisher = "Corporation for National Research Initiatives",
number = "11",

}

Semantics-sensitive retrieval for digital picture libraries. / Wang, James Ze; Chan, Desmond; Li, Jia; Wiederhold, Gio.

In: D-Lib Magazine, Vol. 5, No. 11, 01.11.1999, p. 60-72.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Semantics-sensitive retrieval for digital picture libraries

AU - Wang, James Ze

AU - Chan, Desmond

AU - Li, Jia

AU - Wiederhold, Gio

PY - 1999/11/1

Y1 - 1999/11/1

N2 - We present SIMPLIcity (Semantics-sensitive Integrated Matching for Picture LIbraries), an image database retrieval system, which uses high-level semantics classification and integrated region matching based upon image segmentation. The SIMPLIcity system represents an image by a set of regions, roughly corresponding to objects, which are characterized by color, texture, shape, and location. Based on segmented regions, the system classifies images into categories which are intended to distinguish semantically meaningful differences. These high-level categories, such as textured-nontextured, indoor-outdoor, objectionable-benign, graph-photograph, enhance retrieval by narrowing down the searching range in a database and permitting semantically adaptive searching methods.

AB - We present SIMPLIcity (Semantics-sensitive Integrated Matching for Picture LIbraries), an image database retrieval system, which uses high-level semantics classification and integrated region matching based upon image segmentation. The SIMPLIcity system represents an image by a set of regions, roughly corresponding to objects, which are characterized by color, texture, shape, and location. Based on segmented regions, the system classifies images into categories which are intended to distinguish semantically meaningful differences. These high-level categories, such as textured-nontextured, indoor-outdoor, objectionable-benign, graph-photograph, enhance retrieval by narrowing down the searching range in a database and permitting semantically adaptive searching methods.

UR - http://www.scopus.com/inward/record.url?scp=0003340290&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0003340290&partnerID=8YFLogxK

U2 - 10.1045/november99-wang

DO - 10.1045/november99-wang

M3 - Review article

AN - SCOPUS:0003340290

VL - 5

SP - 60

EP - 72

JO - D-Lib Magazine

JF - D-Lib Magazine

SN - 1082-9873

IS - 11

ER -