Region-based image retrieval using probabilistic feature relevance learning

Byoung Chul Ko, Jing Peng, Hyeran Byun

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Region-Based Image Retrieval (RBIR), a specialisation of content-based image retrieval, is a promising and important research area. RBIR usually requires good segmentation, which is often difficult to achieve in practice for several reasons, such as varying environmental conditions and occlusion. It is, therefore, imperative to develop effective mechanisms for interactive, region-based visual query in order to provide confident retrieval performance. In this paper, we present a novel RBlR system, Finding Region In the Pictures (FRIP), that uses human-centric relevance feedback to create similarity metric on-the-fly in order to overcome some of the limitations associated with RBIR systems. We use features such as colour, texture, normalised area, shape and location, extracted from each region of a segmented image, to represent image content. For each given query, we estimate local feature relevance using probabilistic relevance model, from which to create a flexible metric that is highly adaptive to query location. As a result, local data densities can be sufficiently exploited, whereby rapid performance improvement can be achieved. The efficacy of our method is validated and compared against other competing techniques using real world image data.

Original languageEnglish
Pages (from-to)174-184
Number of pages11
JournalPattern Analysis and Applications
Volume4
Issue number2-3
DOIs
Publication statusPublished - 2001 Dec 1

Fingerprint

Image retrieval
Textures
Color
Feedback

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{c1f5e9f8c297407ebc4a1462fa829360,
title = "Region-based image retrieval using probabilistic feature relevance learning",
abstract = "Region-Based Image Retrieval (RBIR), a specialisation of content-based image retrieval, is a promising and important research area. RBIR usually requires good segmentation, which is often difficult to achieve in practice for several reasons, such as varying environmental conditions and occlusion. It is, therefore, imperative to develop effective mechanisms for interactive, region-based visual query in order to provide confident retrieval performance. In this paper, we present a novel RBlR system, Finding Region In the Pictures (FRIP), that uses human-centric relevance feedback to create similarity metric on-the-fly in order to overcome some of the limitations associated with RBIR systems. We use features such as colour, texture, normalised area, shape and location, extracted from each region of a segmented image, to represent image content. For each given query, we estimate local feature relevance using probabilistic relevance model, from which to create a flexible metric that is highly adaptive to query location. As a result, local data densities can be sufficiently exploited, whereby rapid performance improvement can be achieved. The efficacy of our method is validated and compared against other competing techniques using real world image data.",
author = "Ko, {Byoung Chul} and Jing Peng and Hyeran Byun",
year = "2001",
month = "12",
day = "1",
doi = "10.1007/s100440170015",
language = "English",
volume = "4",
pages = "174--184",
journal = "Pattern Analysis and Applications",
issn = "1433-7541",
publisher = "Springer London",
number = "2-3",

}

Region-based image retrieval using probabilistic feature relevance learning. / Ko, Byoung Chul; Peng, Jing; Byun, Hyeran.

In: Pattern Analysis and Applications, Vol. 4, No. 2-3, 01.12.2001, p. 174-184.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Region-based image retrieval using probabilistic feature relevance learning

AU - Ko, Byoung Chul

AU - Peng, Jing

AU - Byun, Hyeran

PY - 2001/12/1

Y1 - 2001/12/1

N2 - Region-Based Image Retrieval (RBIR), a specialisation of content-based image retrieval, is a promising and important research area. RBIR usually requires good segmentation, which is often difficult to achieve in practice for several reasons, such as varying environmental conditions and occlusion. It is, therefore, imperative to develop effective mechanisms for interactive, region-based visual query in order to provide confident retrieval performance. In this paper, we present a novel RBlR system, Finding Region In the Pictures (FRIP), that uses human-centric relevance feedback to create similarity metric on-the-fly in order to overcome some of the limitations associated with RBIR systems. We use features such as colour, texture, normalised area, shape and location, extracted from each region of a segmented image, to represent image content. For each given query, we estimate local feature relevance using probabilistic relevance model, from which to create a flexible metric that is highly adaptive to query location. As a result, local data densities can be sufficiently exploited, whereby rapid performance improvement can be achieved. The efficacy of our method is validated and compared against other competing techniques using real world image data.

AB - Region-Based Image Retrieval (RBIR), a specialisation of content-based image retrieval, is a promising and important research area. RBIR usually requires good segmentation, which is often difficult to achieve in practice for several reasons, such as varying environmental conditions and occlusion. It is, therefore, imperative to develop effective mechanisms for interactive, region-based visual query in order to provide confident retrieval performance. In this paper, we present a novel RBlR system, Finding Region In the Pictures (FRIP), that uses human-centric relevance feedback to create similarity metric on-the-fly in order to overcome some of the limitations associated with RBIR systems. We use features such as colour, texture, normalised area, shape and location, extracted from each region of a segmented image, to represent image content. For each given query, we estimate local feature relevance using probabilistic relevance model, from which to create a flexible metric that is highly adaptive to query location. As a result, local data densities can be sufficiently exploited, whereby rapid performance improvement can be achieved. The efficacy of our method is validated and compared against other competing techniques using real world image data.

UR - http://www.scopus.com/inward/record.url?scp=0035615180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035615180&partnerID=8YFLogxK

U2 - 10.1007/s100440170015

DO - 10.1007/s100440170015

M3 - Article

AN - SCOPUS:0035615180

VL - 4

SP - 174

EP - 184

JO - Pattern Analysis and Applications

JF - Pattern Analysis and Applications

SN - 1433-7541

IS - 2-3

ER -