Region-based image retrieval using color-size features of watershed regions

Cheng Chieh Chiang, Yi Ping Hung, Hsuan Yang, Greg C. Lee

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

This paper presents a region-based image retrieval system that provides a user interface for helping to specify the watershed regions of interest within a query image. We first propose a new type of visual features, called color-size feature, which includes color-size histogram and moments, to integrate color and region-size information of watershed regions. Next, we design a scheme of region filtering that is based on color-size histogram to fast screen out some of most irrelevant regions and images for the preprocessing of the image retrieval. Our region-based image retrieval system applies the Earth Mover's Distance in the design of the similarity measure for image ranking and matching. Finally, we present some experiments for the color-size feature, region filtering, and retrieval results that demonstrate the efficiency of our proposed system.

Original languageEnglish
Pages (from-to)167-177
Number of pages11
JournalJournal of Visual Communication and Image Representation
Volume20
Issue number3
DOIs
Publication statusPublished - 2009 Apr 1

Fingerprint

Image retrieval
Watersheds
Color
User interfaces
Earth (planet)
Experiments

Keywords

  • Color-size feature
  • Content-based image retrieval
  • Earth mover's distance
  • Region filtering
  • Region-based image retrieval
  • Visual feature

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Region-based image retrieval using color-size features of watershed regions. / Chiang, Cheng Chieh; Hung, Yi Ping; Yang, Hsuan; Lee, Greg C.

In: Journal of Visual Communication and Image Representation, Vol. 20, No. 3, 01.04.2009, p. 167-177.

Research output: Contribution to journalArticle

@article{d16e5e88bd374e84b86e13fac32f16ee,
title = "Region-based image retrieval using color-size features of watershed regions",
abstract = "This paper presents a region-based image retrieval system that provides a user interface for helping to specify the watershed regions of interest within a query image. We first propose a new type of visual features, called color-size feature, which includes color-size histogram and moments, to integrate color and region-size information of watershed regions. Next, we design a scheme of region filtering that is based on color-size histogram to fast screen out some of most irrelevant regions and images for the preprocessing of the image retrieval. Our region-based image retrieval system applies the Earth Mover's Distance in the design of the similarity measure for image ranking and matching. Finally, we present some experiments for the color-size feature, region filtering, and retrieval results that demonstrate the efficiency of our proposed system.",
keywords = "Color-size feature, Content-based image retrieval, Earth mover's distance, Region filtering, Region-based image retrieval, Visual feature",
author = "Chiang, {Cheng Chieh} and Hung, {Yi Ping} and Hsuan Yang and Lee, {Greg C.}",
year = "2009",
month = "4",
day = "1",
doi = "10.1016/j.jvcir.2009.01.001",
language = "English",
volume = "20",
pages = "167--177",
journal = "Journal of Visual Communication and Image Representation",
issn = "1047-3203",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - Region-based image retrieval using color-size features of watershed regions

AU - Chiang, Cheng Chieh

AU - Hung, Yi Ping

AU - Yang, Hsuan

AU - Lee, Greg C.

PY - 2009/4/1

Y1 - 2009/4/1

N2 - This paper presents a region-based image retrieval system that provides a user interface for helping to specify the watershed regions of interest within a query image. We first propose a new type of visual features, called color-size feature, which includes color-size histogram and moments, to integrate color and region-size information of watershed regions. Next, we design a scheme of region filtering that is based on color-size histogram to fast screen out some of most irrelevant regions and images for the preprocessing of the image retrieval. Our region-based image retrieval system applies the Earth Mover's Distance in the design of the similarity measure for image ranking and matching. Finally, we present some experiments for the color-size feature, region filtering, and retrieval results that demonstrate the efficiency of our proposed system.

AB - This paper presents a region-based image retrieval system that provides a user interface for helping to specify the watershed regions of interest within a query image. We first propose a new type of visual features, called color-size feature, which includes color-size histogram and moments, to integrate color and region-size information of watershed regions. Next, we design a scheme of region filtering that is based on color-size histogram to fast screen out some of most irrelevant regions and images for the preprocessing of the image retrieval. Our region-based image retrieval system applies the Earth Mover's Distance in the design of the similarity measure for image ranking and matching. Finally, we present some experiments for the color-size feature, region filtering, and retrieval results that demonstrate the efficiency of our proposed system.

KW - Color-size feature

KW - Content-based image retrieval

KW - Earth mover's distance

KW - Region filtering

KW - Region-based image retrieval

KW - Visual feature

UR - http://www.scopus.com/inward/record.url?scp=61749096344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61749096344&partnerID=8YFLogxK

U2 - 10.1016/j.jvcir.2009.01.001

DO - 10.1016/j.jvcir.2009.01.001

M3 - Article

AN - SCOPUS:61749096344

VL - 20

SP - 167

EP - 177

JO - Journal of Visual Communication and Image Representation

JF - Journal of Visual Communication and Image Representation

SN - 1047-3203

IS - 3

ER -