Fuzzy art-based image clustering method for content-based image retrieval

Sang Sung Park, Kwang K. Seo, Dong Sik Jang

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In this paper, an image clustering method that is essential for content-based image retrieval in large image databases efficiently is proposed by color, texture, and shape contents. The dominant triple HSV (Hue, Saturation, and Value), which are extracted from quantized HSV joint histogram in the image region, are used for representing color information in the image. Entropy and maximum entry from co-occurrence matrices are used for texture information and edge angle histogram is used for representing shape information. Due to its algorithmic simplicity and the several merits that facilitate the implementation of the neural network, Fuzzy ART has been exploited for image clustering. Original Fuzzy ART suffers unnecessary increase of the number of output neurons when the noise input is presented. Therefore, the improved Fuzzy ART algorithm is proposed to resolve the problem by differently updating the committed node and uncommitted node, and checking the vigilance test again. To show the validity of the proposed algorithm, experimental results on image clustering performance and comparison with original Fuzzy ART are presented in terms of recall rates.

Original languageEnglish
Pages (from-to)213-233
Number of pages21
JournalInternational Journal of Information Technology and Decision Making
Volume6
Issue number2
DOIs
Publication statusPublished - 2007 Jun 1

Fingerprint

Image retrieval
Textures
Color
Fuzzy neural networks
Neurons
Entropy

Keywords

  • Content-based image retrieval
  • Feature vector
  • Fuzzy ART
  • Image clustering

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Fuzzy art-based image clustering method for content-based image retrieval. / Park, Sang Sung; Seo, Kwang K.; Jang, Dong Sik.

In: International Journal of Information Technology and Decision Making, Vol. 6, No. 2, 01.06.2007, p. 213-233.

Research output: Contribution to journalArticle

@article{9389a6baeb2049e497a2b5903b227211,
title = "Fuzzy art-based image clustering method for content-based image retrieval",
abstract = "In this paper, an image clustering method that is essential for content-based image retrieval in large image databases efficiently is proposed by color, texture, and shape contents. The dominant triple HSV (Hue, Saturation, and Value), which are extracted from quantized HSV joint histogram in the image region, are used for representing color information in the image. Entropy and maximum entry from co-occurrence matrices are used for texture information and edge angle histogram is used for representing shape information. Due to its algorithmic simplicity and the several merits that facilitate the implementation of the neural network, Fuzzy ART has been exploited for image clustering. Original Fuzzy ART suffers unnecessary increase of the number of output neurons when the noise input is presented. Therefore, the improved Fuzzy ART algorithm is proposed to resolve the problem by differently updating the committed node and uncommitted node, and checking the vigilance test again. To show the validity of the proposed algorithm, experimental results on image clustering performance and comparison with original Fuzzy ART are presented in terms of recall rates.",
keywords = "Content-based image retrieval, Feature vector, Fuzzy ART, Image clustering",
author = "Park, {Sang Sung} and Seo, {Kwang K.} and Jang, {Dong Sik}",
year = "2007",
month = "6",
day = "1",
doi = "10.1142/S0219622007002496",
language = "English",
volume = "6",
pages = "213--233",
journal = "International Journal of Information Technology and Decision Making",
issn = "0219-6220",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2",

}

TY - JOUR

T1 - Fuzzy art-based image clustering method for content-based image retrieval

AU - Park, Sang Sung

AU - Seo, Kwang K.

AU - Jang, Dong Sik

PY - 2007/6/1

Y1 - 2007/6/1

N2 - In this paper, an image clustering method that is essential for content-based image retrieval in large image databases efficiently is proposed by color, texture, and shape contents. The dominant triple HSV (Hue, Saturation, and Value), which are extracted from quantized HSV joint histogram in the image region, are used for representing color information in the image. Entropy and maximum entry from co-occurrence matrices are used for texture information and edge angle histogram is used for representing shape information. Due to its algorithmic simplicity and the several merits that facilitate the implementation of the neural network, Fuzzy ART has been exploited for image clustering. Original Fuzzy ART suffers unnecessary increase of the number of output neurons when the noise input is presented. Therefore, the improved Fuzzy ART algorithm is proposed to resolve the problem by differently updating the committed node and uncommitted node, and checking the vigilance test again. To show the validity of the proposed algorithm, experimental results on image clustering performance and comparison with original Fuzzy ART are presented in terms of recall rates.

AB - In this paper, an image clustering method that is essential for content-based image retrieval in large image databases efficiently is proposed by color, texture, and shape contents. The dominant triple HSV (Hue, Saturation, and Value), which are extracted from quantized HSV joint histogram in the image region, are used for representing color information in the image. Entropy and maximum entry from co-occurrence matrices are used for texture information and edge angle histogram is used for representing shape information. Due to its algorithmic simplicity and the several merits that facilitate the implementation of the neural network, Fuzzy ART has been exploited for image clustering. Original Fuzzy ART suffers unnecessary increase of the number of output neurons when the noise input is presented. Therefore, the improved Fuzzy ART algorithm is proposed to resolve the problem by differently updating the committed node and uncommitted node, and checking the vigilance test again. To show the validity of the proposed algorithm, experimental results on image clustering performance and comparison with original Fuzzy ART are presented in terms of recall rates.

KW - Content-based image retrieval

KW - Feature vector

KW - Fuzzy ART

KW - Image clustering

UR - http://www.scopus.com/inward/record.url?scp=34547324175&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547324175&partnerID=8YFLogxK

U2 - 10.1142/S0219622007002496

DO - 10.1142/S0219622007002496

M3 - Article

VL - 6

SP - 213

EP - 233

JO - International Journal of Information Technology and Decision Making

JF - International Journal of Information Technology and Decision Making

SN - 0219-6220

IS - 2

ER -