Retrieval and performance evaluation of artificially-produced images

Nursuriati Jamil, Tengku Mohd Tengku Sembok, Zainab Abu Bakar

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

Abstract

Artificially-produced images are stylized form of natural, real-life objects such as animals, flora or human. Motifs are repeated elements typically found in textile or architectural design. They are considered as artificially-produced objects as they are customarily symbolic representations of natural objects. This paper describes and tests the efficiency of retrieving motifs using different combination of five geometric shape descriptors: eccentricity, compactness, convexity, rectangularity and solidity. Even though there are many existing approaches of shape-based image retrievals, the goal of this paper is to identify the fewest necessary shape descriptors to characterize the motif shape adequately so that it may be unambiguously retrieved or identified. Fifty selected songket motifs are used as sample queries in this paper. Similarities of these motifs are measured using Euclidean distance and performances of the retrievals are evaluated using both quantitative and qualitative tests. Quantitative test using recall-precision rate shows that geometric shape descriptors are effective in retrieving the songket motifs. However, qualitative test results demonstrate agreement between the system and the interviewed people in the assignment of similarity ranks is at average level.

Original languageEnglish
Title of host publicationProceedings of the 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008
Pages345-350
Number of pages6
Publication statusPublished - 2008
Externally publishedYes
Event8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008 - Palma de Mallorca
Duration: 1 Sep 20083 Sep 2008

Other

Other8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008
CityPalma de Mallorca
Period1/9/083/9/08

Fingerprint

Architectural design
Image retrieval
Textiles
Animals

Keywords

  • Artificially-produced image
  • Content-based image retrieval
  • Geometric shape descriptors
  • Performance evaluation
  • Songket motifs

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Jamil, N., Sembok, T. M. T., & Bakar, Z. A. (2008). Retrieval and performance evaluation of artificially-produced images. In Proceedings of the 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008 (pp. 345-350)

Retrieval and performance evaluation of artificially-produced images. / Jamil, Nursuriati; Sembok, Tengku Mohd Tengku; Bakar, Zainab Abu.

Proceedings of the 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008. 2008. p. 345-350.

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

Jamil, N, Sembok, TMT & Bakar, ZA 2008, Retrieval and performance evaluation of artificially-produced images. in Proceedings of the 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008. pp. 345-350, 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008, Palma de Mallorca, 1/9/08.
Jamil N, Sembok TMT, Bakar ZA. Retrieval and performance evaluation of artificially-produced images. In Proceedings of the 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008. 2008. p. 345-350
Jamil, Nursuriati ; Sembok, Tengku Mohd Tengku ; Bakar, Zainab Abu. / Retrieval and performance evaluation of artificially-produced images. Proceedings of the 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008. 2008. pp. 345-350
@inproceedings{acdbca4fd3504bbe80c9b7f661c9f9ec,
title = "Retrieval and performance evaluation of artificially-produced images",
abstract = "Artificially-produced images are stylized form of natural, real-life objects such as animals, flora or human. Motifs are repeated elements typically found in textile or architectural design. They are considered as artificially-produced objects as they are customarily symbolic representations of natural objects. This paper describes and tests the efficiency of retrieving motifs using different combination of five geometric shape descriptors: eccentricity, compactness, convexity, rectangularity and solidity. Even though there are many existing approaches of shape-based image retrievals, the goal of this paper is to identify the fewest necessary shape descriptors to characterize the motif shape adequately so that it may be unambiguously retrieved or identified. Fifty selected songket motifs are used as sample queries in this paper. Similarities of these motifs are measured using Euclidean distance and performances of the retrievals are evaluated using both quantitative and qualitative tests. Quantitative test using recall-precision rate shows that geometric shape descriptors are effective in retrieving the songket motifs. However, qualitative test results demonstrate agreement between the system and the interviewed people in the assignment of similarity ranks is at average level.",
keywords = "Artificially-produced image, Content-based image retrieval, Geometric shape descriptors, Performance evaluation, Songket motifs",
author = "Nursuriati Jamil and Sembok, {Tengku Mohd Tengku} and Bakar, {Zainab Abu}",
year = "2008",
language = "English",
isbn = "9780889867598",
pages = "345--350",
booktitle = "Proceedings of the 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008",

}

TY - GEN

T1 - Retrieval and performance evaluation of artificially-produced images

AU - Jamil, Nursuriati

AU - Sembok, Tengku Mohd Tengku

AU - Bakar, Zainab Abu

PY - 2008

Y1 - 2008

N2 - Artificially-produced images are stylized form of natural, real-life objects such as animals, flora or human. Motifs are repeated elements typically found in textile or architectural design. They are considered as artificially-produced objects as they are customarily symbolic representations of natural objects. This paper describes and tests the efficiency of retrieving motifs using different combination of five geometric shape descriptors: eccentricity, compactness, convexity, rectangularity and solidity. Even though there are many existing approaches of shape-based image retrievals, the goal of this paper is to identify the fewest necessary shape descriptors to characterize the motif shape adequately so that it may be unambiguously retrieved or identified. Fifty selected songket motifs are used as sample queries in this paper. Similarities of these motifs are measured using Euclidean distance and performances of the retrievals are evaluated using both quantitative and qualitative tests. Quantitative test using recall-precision rate shows that geometric shape descriptors are effective in retrieving the songket motifs. However, qualitative test results demonstrate agreement between the system and the interviewed people in the assignment of similarity ranks is at average level.

AB - Artificially-produced images are stylized form of natural, real-life objects such as animals, flora or human. Motifs are repeated elements typically found in textile or architectural design. They are considered as artificially-produced objects as they are customarily symbolic representations of natural objects. This paper describes and tests the efficiency of retrieving motifs using different combination of five geometric shape descriptors: eccentricity, compactness, convexity, rectangularity and solidity. Even though there are many existing approaches of shape-based image retrievals, the goal of this paper is to identify the fewest necessary shape descriptors to characterize the motif shape adequately so that it may be unambiguously retrieved or identified. Fifty selected songket motifs are used as sample queries in this paper. Similarities of these motifs are measured using Euclidean distance and performances of the retrievals are evaluated using both quantitative and qualitative tests. Quantitative test using recall-precision rate shows that geometric shape descriptors are effective in retrieving the songket motifs. However, qualitative test results demonstrate agreement between the system and the interviewed people in the assignment of similarity ranks is at average level.

KW - Artificially-produced image

KW - Content-based image retrieval

KW - Geometric shape descriptors

KW - Performance evaluation

KW - Songket motifs

UR - http://www.scopus.com/inward/record.url?scp=84887297854&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887297854&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84887297854

SN - 9780889867598

SP - 345

EP - 350

BT - Proceedings of the 8th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2008

ER -