An image search system with analytical functions for 3D color vector quantization and cluster-based shape and structure features

Ali Ridho Barakbah, Yasushi Kiyoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The application area of image retrieval systems has widely spread to the WWW and multimedia database environments. This paper presents an image search system with analytical functions for combining shape, structure, and color features. The system pre-processes an image segmentation from hybrid color systems of HSL and CIELAB. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system extracts three features of an image which are color, shape and structure. We apply the 3D Color Vector Quantization for the color feature extraction. The shape properties of an image which include eccentricity, area, equivalent diameter, and convex area, are analyzed for extracting the shape feature. The image structure is identified by applying 2D Forward Mirror-Extended Curvelet Transform. Another distinctive idea introduced in this paper is a new distance metric which represents a semantic similarity. This paper has evaluations of the system using 1000 JPEG images from COREL image collections. The experimental results clarify the feasibility and effectiveness of the proposed system to improve accuracy for image retrieval.

Original languageEnglish
Title of host publicationFrontiers in Artificial Intelligence and Applications
Pages168-187
Number of pages20
Volume206
DOIs
Publication statusPublished - 2010

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume206
ISSN (Print)09226389

Fingerprint

Vector quantization
Color
Image retrieval
Image resolution
Image segmentation
World Wide Web
Feature extraction
Mirrors
Semantics
Mathematical transformations

Keywords

  • CBIR
  • Distance metric
  • Feature extraction
  • Image retrieval
  • Image segmentation

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Barakbah, A. R., & Kiyoki, Y. (2010). An image search system with analytical functions for 3D color vector quantization and cluster-based shape and structure features. In Frontiers in Artificial Intelligence and Applications (Vol. 206, pp. 168-187). (Frontiers in Artificial Intelligence and Applications; Vol. 206). https://doi.org/10.3233/978-1-60750-477-1-169

An image search system with analytical functions for 3D color vector quantization and cluster-based shape and structure features. / Barakbah, Ali Ridho; Kiyoki, Yasushi.

Frontiers in Artificial Intelligence and Applications. Vol. 206 2010. p. 168-187 (Frontiers in Artificial Intelligence and Applications; Vol. 206).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Barakbah, AR & Kiyoki, Y 2010, An image search system with analytical functions for 3D color vector quantization and cluster-based shape and structure features. in Frontiers in Artificial Intelligence and Applications. vol. 206, Frontiers in Artificial Intelligence and Applications, vol. 206, pp. 168-187. https://doi.org/10.3233/978-1-60750-477-1-169
Barakbah AR, Kiyoki Y. An image search system with analytical functions for 3D color vector quantization and cluster-based shape and structure features. In Frontiers in Artificial Intelligence and Applications. Vol. 206. 2010. p. 168-187. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-60750-477-1-169
Barakbah, Ali Ridho ; Kiyoki, Yasushi. / An image search system with analytical functions for 3D color vector quantization and cluster-based shape and structure features. Frontiers in Artificial Intelligence and Applications. Vol. 206 2010. pp. 168-187 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{82f3e15599704edd856aa135a910b667,
title = "An image search system with analytical functions for 3D color vector quantization and cluster-based shape and structure features",
abstract = "The application area of image retrieval systems has widely spread to the WWW and multimedia database environments. This paper presents an image search system with analytical functions for combining shape, structure, and color features. The system pre-processes an image segmentation from hybrid color systems of HSL and CIELAB. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system extracts three features of an image which are color, shape and structure. We apply the 3D Color Vector Quantization for the color feature extraction. The shape properties of an image which include eccentricity, area, equivalent diameter, and convex area, are analyzed for extracting the shape feature. The image structure is identified by applying 2D Forward Mirror-Extended Curvelet Transform. Another distinctive idea introduced in this paper is a new distance metric which represents a semantic similarity. This paper has evaluations of the system using 1000 JPEG images from COREL image collections. The experimental results clarify the feasibility and effectiveness of the proposed system to improve accuracy for image retrieval.",
keywords = "CBIR, Distance metric, Feature extraction, Image retrieval, Image segmentation",
author = "Barakbah, {Ali Ridho} and Yasushi Kiyoki",
year = "2010",
doi = "10.3233/978-1-60750-477-1-169",
language = "English",
isbn = "9781607500896",
volume = "206",
series = "Frontiers in Artificial Intelligence and Applications",
pages = "168--187",
booktitle = "Frontiers in Artificial Intelligence and Applications",

}

TY - GEN

T1 - An image search system with analytical functions for 3D color vector quantization and cluster-based shape and structure features

AU - Barakbah, Ali Ridho

AU - Kiyoki, Yasushi

PY - 2010

Y1 - 2010

N2 - The application area of image retrieval systems has widely spread to the WWW and multimedia database environments. This paper presents an image search system with analytical functions for combining shape, structure, and color features. The system pre-processes an image segmentation from hybrid color systems of HSL and CIELAB. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system extracts three features of an image which are color, shape and structure. We apply the 3D Color Vector Quantization for the color feature extraction. The shape properties of an image which include eccentricity, area, equivalent diameter, and convex area, are analyzed for extracting the shape feature. The image structure is identified by applying 2D Forward Mirror-Extended Curvelet Transform. Another distinctive idea introduced in this paper is a new distance metric which represents a semantic similarity. This paper has evaluations of the system using 1000 JPEG images from COREL image collections. The experimental results clarify the feasibility and effectiveness of the proposed system to improve accuracy for image retrieval.

AB - The application area of image retrieval systems has widely spread to the WWW and multimedia database environments. This paper presents an image search system with analytical functions for combining shape, structure, and color features. The system pre-processes an image segmentation from hybrid color systems of HSL and CIELAB. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system extracts three features of an image which are color, shape and structure. We apply the 3D Color Vector Quantization for the color feature extraction. The shape properties of an image which include eccentricity, area, equivalent diameter, and convex area, are analyzed for extracting the shape feature. The image structure is identified by applying 2D Forward Mirror-Extended Curvelet Transform. Another distinctive idea introduced in this paper is a new distance metric which represents a semantic similarity. This paper has evaluations of the system using 1000 JPEG images from COREL image collections. The experimental results clarify the feasibility and effectiveness of the proposed system to improve accuracy for image retrieval.

KW - CBIR

KW - Distance metric

KW - Feature extraction

KW - Image retrieval

KW - Image segmentation

UR - http://www.scopus.com/inward/record.url?scp=77951005879&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951005879&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-477-1-169

DO - 10.3233/978-1-60750-477-1-169

M3 - Conference contribution

SN - 9781607500896

VL - 206

T3 - Frontiers in Artificial Intelligence and Applications

SP - 168

EP - 187

BT - Frontiers in Artificial Intelligence and Applications

ER -