Quantitative and qualitative performance evaluations of artificially-produced images

Nursuriati Jamil, Zainab Abu Bakar, Tengku Mohd Tengku Sembok

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

Abstract

Even though researches in content-based image retrieval are one of the most intensive research areas of information retrieval, they almost certainly focused on retrieving natural images or photographs. Artificially-produced images are stylized form of natural, real-life objects. Research for these images have received less attention, thus this paper attempts to intensify work in this area by implementing quantitative and qualitative performance evaluation of artificially-produced images. Fifty selected images are used as sample queries and they are retrieved based on fusion of geometric shape descriptors. Similarities of these images are measured using Euclidean distance and performances of the retrievals are evaluated using both quantitative and qualitative tests. Quantitative test using recall-precision rate and hit-miss ratio showed that geometric shape descriptors are effective in retrieving the images. 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 - 2010 International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10
Pages113-118
Number of pages6
DOIs
Publication statusPublished - 2010
Externally publishedYes
EventInternational Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10 - Shah Alam
Duration: 17 Mar 201018 Mar 2010

Other

OtherInternational Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10
CityShah Alam
Period17/3/1018/3/10

Fingerprint

Image retrieval
Information retrieval
Fusion reactions

Keywords

  • Artificially-produced images
  • Geometric shape descriptor
  • Image retrieval
  • Performance evaluation

ASJC Scopus subject areas

  • Information Systems

Cite this

Jamil, N., Abu Bakar, Z., & Sembok, T. M. T. (2010). Quantitative and qualitative performance evaluations of artificially-produced images. In Proceedings - 2010 International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10 (pp. 113-118). [5466937] https://doi.org/10.1109/INFRKM.2010.5466937

Quantitative and qualitative performance evaluations of artificially-produced images. / Jamil, Nursuriati; Abu Bakar, Zainab; Sembok, Tengku Mohd Tengku.

Proceedings - 2010 International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10. 2010. p. 113-118 5466937.

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

Jamil, N, Abu Bakar, Z & Sembok, TMT 2010, Quantitative and qualitative performance evaluations of artificially-produced images. in Proceedings - 2010 International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10., 5466937, pp. 113-118, International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10, Shah Alam, 17/3/10. https://doi.org/10.1109/INFRKM.2010.5466937
Jamil N, Abu Bakar Z, Sembok TMT. Quantitative and qualitative performance evaluations of artificially-produced images. In Proceedings - 2010 International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10. 2010. p. 113-118. 5466937 https://doi.org/10.1109/INFRKM.2010.5466937
Jamil, Nursuriati ; Abu Bakar, Zainab ; Sembok, Tengku Mohd Tengku. / Quantitative and qualitative performance evaluations of artificially-produced images. Proceedings - 2010 International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10. 2010. pp. 113-118
@inproceedings{d654eeafa03e4074ad2aa556bd05677a,
title = "Quantitative and qualitative performance evaluations of artificially-produced images",
abstract = "Even though researches in content-based image retrieval are one of the most intensive research areas of information retrieval, they almost certainly focused on retrieving natural images or photographs. Artificially-produced images are stylized form of natural, real-life objects. Research for these images have received less attention, thus this paper attempts to intensify work in this area by implementing quantitative and qualitative performance evaluation of artificially-produced images. Fifty selected images are used as sample queries and they are retrieved based on fusion of geometric shape descriptors. Similarities of these images are measured using Euclidean distance and performances of the retrievals are evaluated using both quantitative and qualitative tests. Quantitative test using recall-precision rate and hit-miss ratio showed that geometric shape descriptors are effective in retrieving the images. 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 images, Geometric shape descriptor, Image retrieval, Performance evaluation",
author = "Nursuriati Jamil and {Abu Bakar}, Zainab and Sembok, {Tengku Mohd Tengku}",
year = "2010",
doi = "10.1109/INFRKM.2010.5466937",
language = "English",
isbn = "9781424456512",
pages = "113--118",
booktitle = "Proceedings - 2010 International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10",

}

TY - GEN

T1 - Quantitative and qualitative performance evaluations of artificially-produced images

AU - Jamil, Nursuriati

AU - Abu Bakar, Zainab

AU - Sembok, Tengku Mohd Tengku

PY - 2010

Y1 - 2010

N2 - Even though researches in content-based image retrieval are one of the most intensive research areas of information retrieval, they almost certainly focused on retrieving natural images or photographs. Artificially-produced images are stylized form of natural, real-life objects. Research for these images have received less attention, thus this paper attempts to intensify work in this area by implementing quantitative and qualitative performance evaluation of artificially-produced images. Fifty selected images are used as sample queries and they are retrieved based on fusion of geometric shape descriptors. Similarities of these images are measured using Euclidean distance and performances of the retrievals are evaluated using both quantitative and qualitative tests. Quantitative test using recall-precision rate and hit-miss ratio showed that geometric shape descriptors are effective in retrieving the images. However, qualitative test results demonstrate agreement between the system and the interviewed people in the assignment of similarity ranks is at average level.

AB - Even though researches in content-based image retrieval are one of the most intensive research areas of information retrieval, they almost certainly focused on retrieving natural images or photographs. Artificially-produced images are stylized form of natural, real-life objects. Research for these images have received less attention, thus this paper attempts to intensify work in this area by implementing quantitative and qualitative performance evaluation of artificially-produced images. Fifty selected images are used as sample queries and they are retrieved based on fusion of geometric shape descriptors. Similarities of these images are measured using Euclidean distance and performances of the retrievals are evaluated using both quantitative and qualitative tests. Quantitative test using recall-precision rate and hit-miss ratio showed that geometric shape descriptors are effective in retrieving the images. 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 images

KW - Geometric shape descriptor

KW - Image retrieval

KW - Performance evaluation

UR - http://www.scopus.com/inward/record.url?scp=77953911023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953911023&partnerID=8YFLogxK

U2 - 10.1109/INFRKM.2010.5466937

DO - 10.1109/INFRKM.2010.5466937

M3 - Conference contribution

SN - 9781424456512

SP - 113

EP - 118

BT - Proceedings - 2010 International Conference on Information Retrieval and Knowledge Management: Exploring the Invisible World, CAMP'10

ER -