A dynamic user concept pattern learning framework for content-based image retrieval

Shu Ching Chen, Stuart H. Rubin, Mei-Ling Shyu, Chengcui Zhang

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

A rapid increase in the amount of image data and the inefficiency of traditional text-based image retrieval systems have served to make content-based image retrieval an active research field. It is crucial to effectively discover users' concept patterns through an acquired understanding of the subjective role played by humans in the retrieval process for such systems. A learning and retrieval framework is used to achieve this. It seamlessly incorporates multiple instance learning for relevant feedback to discover users concept patterns - especially in the region of greatest user interest. It also maps the local feature vector of that region to the high-level concept pattern. This underlying mapping can be progressively discovered through feedback and learning. The user guides the retrieval systems learning process using his/her focus of attention. Retrieval performance is tested to establish the feasibility and effectiveness of the proposed learning and retrieval framework.

Original languageEnglish
Pages (from-to)772-783
Number of pages12
JournalIEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
Volume36
Issue number6
DOIs
StatePublished - Nov 1 2006

Fingerprint

Image retrieval
Feedback
Learning systems

Keywords

  • Content-based image retrieval (CBIR)
  • Multiple instance learning
  • Neural network
  • Relevance feedback

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence
  • Human-Computer Interaction
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

A dynamic user concept pattern learning framework for content-based image retrieval. / Chen, Shu Ching; Rubin, Stuart H.; Shyu, Mei-Ling; Zhang, Chengcui.

In: IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, Vol. 36, No. 6, 01.11.2006, p. 772-783.

Research output: Contribution to journalArticle

@article{a5f72a8f6db0405c909b958a8b5fe1ba,
title = "A dynamic user concept pattern learning framework for content-based image retrieval",
abstract = "A rapid increase in the amount of image data and the inefficiency of traditional text-based image retrieval systems have served to make content-based image retrieval an active research field. It is crucial to effectively discover users' concept patterns through an acquired understanding of the subjective role played by humans in the retrieval process for such systems. A learning and retrieval framework is used to achieve this. It seamlessly incorporates multiple instance learning for relevant feedback to discover users concept patterns - especially in the region of greatest user interest. It also maps the local feature vector of that region to the high-level concept pattern. This underlying mapping can be progressively discovered through feedback and learning. The user guides the retrieval systems learning process using his/her focus of attention. Retrieval performance is tested to establish the feasibility and effectiveness of the proposed learning and retrieval framework.",
keywords = "Content-based image retrieval (CBIR), Multiple instance learning, Neural network, Relevance feedback",
author = "Chen, {Shu Ching} and Rubin, {Stuart H.} and Mei-Ling Shyu and Chengcui Zhang",
year = "2006",
month = "11",
day = "1",
doi = "10.1109/TSMCC.2006.855507",
language = "English",
volume = "36",
pages = "772--783",
journal = "IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews",
issn = "1094-6977",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - A dynamic user concept pattern learning framework for content-based image retrieval

AU - Chen, Shu Ching

AU - Rubin, Stuart H.

AU - Shyu, Mei-Ling

AU - Zhang, Chengcui

PY - 2006/11/1

Y1 - 2006/11/1

N2 - A rapid increase in the amount of image data and the inefficiency of traditional text-based image retrieval systems have served to make content-based image retrieval an active research field. It is crucial to effectively discover users' concept patterns through an acquired understanding of the subjective role played by humans in the retrieval process for such systems. A learning and retrieval framework is used to achieve this. It seamlessly incorporates multiple instance learning for relevant feedback to discover users concept patterns - especially in the region of greatest user interest. It also maps the local feature vector of that region to the high-level concept pattern. This underlying mapping can be progressively discovered through feedback and learning. The user guides the retrieval systems learning process using his/her focus of attention. Retrieval performance is tested to establish the feasibility and effectiveness of the proposed learning and retrieval framework.

AB - A rapid increase in the amount of image data and the inefficiency of traditional text-based image retrieval systems have served to make content-based image retrieval an active research field. It is crucial to effectively discover users' concept patterns through an acquired understanding of the subjective role played by humans in the retrieval process for such systems. A learning and retrieval framework is used to achieve this. It seamlessly incorporates multiple instance learning for relevant feedback to discover users concept patterns - especially in the region of greatest user interest. It also maps the local feature vector of that region to the high-level concept pattern. This underlying mapping can be progressively discovered through feedback and learning. The user guides the retrieval systems learning process using his/her focus of attention. Retrieval performance is tested to establish the feasibility and effectiveness of the proposed learning and retrieval framework.

KW - Content-based image retrieval (CBIR)

KW - Multiple instance learning

KW - Neural network

KW - Relevance feedback

UR - http://www.scopus.com/inward/record.url?scp=33750598171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750598171&partnerID=8YFLogxK

U2 - 10.1109/TSMCC.2006.855507

DO - 10.1109/TSMCC.2006.855507

M3 - Article

VL - 36

SP - 772

EP - 783

JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

SN - 1094-6977

IS - 6

ER -