CLUE: Cluster-based retrieval of images by unsupervised learning

Yixin Chen, James Z. Wang, Robert Krovetz

Research output: Contribution to journalArticle

212 Citations (Scopus)

Abstract

In a typical content-based image retrieval (CBIR) system, target images (images in the database) are sorted by feature similarities with respect to the query. Similarities among target images are usually ignored. This paper introduces a new technique, cluster-based retrieval of images by unsupervised learning (CLUE), for improving user interaction with image retrieval systems by fully exploiting the similarity information. CLUE retrieves image clusters by applying a graph-theoretic clustering algorithm to a collection of images in the vicinity of the query. Clustering in CLUE is dynamic. In particular, clusters formed depend on which images are retrieved in response to the query. CLUE can be combined with any real-valued symmetric similarity measure (metric or nonmetric). Thus, it may be embedded in many current CBIR systems, including relevance feedback systems. The performance of an experimental image retrieval system using CLUE is evaluated on a database of around 60,000 images from COREL. Empirical results demonstrate improved performance compared with a CBIR system using the same image similarity measure. In addition, results on images returned by Google's Image Search reveal the potential of applying CLUE to real-world image data and integrating CLUE as a part of the interface for keyword-based image retrieval systems.

Original languageEnglish (US)
Pages (from-to)1187-1201
Number of pages15
JournalIEEE Transactions on Image Processing
Volume14
Issue number8
DOIs
StatePublished - Aug 1 2005

Fingerprint

Unsupervised learning
Image retrieval
Clustering algorithms
Feedback

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

@article{a1e89bfb3dd2422ca5b90516082fb23e,
title = "CLUE: Cluster-based retrieval of images by unsupervised learning",
abstract = "In a typical content-based image retrieval (CBIR) system, target images (images in the database) are sorted by feature similarities with respect to the query. Similarities among target images are usually ignored. This paper introduces a new technique, cluster-based retrieval of images by unsupervised learning (CLUE), for improving user interaction with image retrieval systems by fully exploiting the similarity information. CLUE retrieves image clusters by applying a graph-theoretic clustering algorithm to a collection of images in the vicinity of the query. Clustering in CLUE is dynamic. In particular, clusters formed depend on which images are retrieved in response to the query. CLUE can be combined with any real-valued symmetric similarity measure (metric or nonmetric). Thus, it may be embedded in many current CBIR systems, including relevance feedback systems. The performance of an experimental image retrieval system using CLUE is evaluated on a database of around 60,000 images from COREL. Empirical results demonstrate improved performance compared with a CBIR system using the same image similarity measure. In addition, results on images returned by Google's Image Search reveal the potential of applying CLUE to real-world image data and integrating CLUE as a part of the interface for keyword-based image retrieval systems.",
author = "Yixin Chen and Wang, {James Z.} and Robert Krovetz",
year = "2005",
month = "8",
day = "1",
doi = "10.1109/TIP.2005.849770",
language = "English (US)",
volume = "14",
pages = "1187--1201",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

CLUE : Cluster-based retrieval of images by unsupervised learning. / Chen, Yixin; Wang, James Z.; Krovetz, Robert.

In: IEEE Transactions on Image Processing, Vol. 14, No. 8, 01.08.2005, p. 1187-1201.

Research output: Contribution to journalArticle

TY - JOUR

T1 - CLUE

T2 - Cluster-based retrieval of images by unsupervised learning

AU - Chen, Yixin

AU - Wang, James Z.

AU - Krovetz, Robert

PY - 2005/8/1

Y1 - 2005/8/1

N2 - In a typical content-based image retrieval (CBIR) system, target images (images in the database) are sorted by feature similarities with respect to the query. Similarities among target images are usually ignored. This paper introduces a new technique, cluster-based retrieval of images by unsupervised learning (CLUE), for improving user interaction with image retrieval systems by fully exploiting the similarity information. CLUE retrieves image clusters by applying a graph-theoretic clustering algorithm to a collection of images in the vicinity of the query. Clustering in CLUE is dynamic. In particular, clusters formed depend on which images are retrieved in response to the query. CLUE can be combined with any real-valued symmetric similarity measure (metric or nonmetric). Thus, it may be embedded in many current CBIR systems, including relevance feedback systems. The performance of an experimental image retrieval system using CLUE is evaluated on a database of around 60,000 images from COREL. Empirical results demonstrate improved performance compared with a CBIR system using the same image similarity measure. In addition, results on images returned by Google's Image Search reveal the potential of applying CLUE to real-world image data and integrating CLUE as a part of the interface for keyword-based image retrieval systems.

AB - In a typical content-based image retrieval (CBIR) system, target images (images in the database) are sorted by feature similarities with respect to the query. Similarities among target images are usually ignored. This paper introduces a new technique, cluster-based retrieval of images by unsupervised learning (CLUE), for improving user interaction with image retrieval systems by fully exploiting the similarity information. CLUE retrieves image clusters by applying a graph-theoretic clustering algorithm to a collection of images in the vicinity of the query. Clustering in CLUE is dynamic. In particular, clusters formed depend on which images are retrieved in response to the query. CLUE can be combined with any real-valued symmetric similarity measure (metric or nonmetric). Thus, it may be embedded in many current CBIR systems, including relevance feedback systems. The performance of an experimental image retrieval system using CLUE is evaluated on a database of around 60,000 images from COREL. Empirical results demonstrate improved performance compared with a CBIR system using the same image similarity measure. In addition, results on images returned by Google's Image Search reveal the potential of applying CLUE to real-world image data and integrating CLUE as a part of the interface for keyword-based image retrieval systems.

UR - http://www.scopus.com/inward/record.url?scp=24144495321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24144495321&partnerID=8YFLogxK

U2 - 10.1109/TIP.2005.849770

DO - 10.1109/TIP.2005.849770

M3 - Article

C2 - 16121465

AN - SCOPUS:24144495321

VL - 14

SP - 1187

EP - 1201

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 8

ER -