A method for evaluating the performance of content-based image retrieval systems

J. A. Black, G. Fahmy, Sethuraman Panchanathan

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

10 Citations (Scopus)

Abstract

In recent years multimedia researchers have attempted to design content-based image retrieval systems. However, despite the development of these systems, the term "content" has still remained rather ill defined, and this has made the evaluation of such systems problematic. This paper proposes a method for the creation of a test set of images in which the similarity of each image pair is estimated by two independent methods - by the subjective evaluation of human observers, and by the use of "content words" as basis vectors that allow the multidimensional content of each image to be represented with a content vector. The latter method is shown to correlate with the subjective judgement of human observers, and thus provide both a more objective method for evaluating and expressing image content, and a possible path to automating the process in the future.

Original languageEnglish (US)
Title of host publicationProceedings - 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages96-100
Number of pages5
Volume2002-January
ISBN (Electronic)0769515371
DOIs
StatePublished - 2002
Event5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002 - Santa Fe, United States
Duration: Apr 7 2002Apr 9 2002

Other

Other5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002
CountryUnited States
CitySanta Fe
Period4/7/024/9/02

Fingerprint

Image retrieval

Keywords

  • Character recognition
  • Content based retrieval
  • Humans
  • Image databases
  • Image retrieval
  • Multimedia databases
  • Multimedia systems
  • Pattern recognition
  • Raw materials
  • Testing

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Black, J. A., Fahmy, G., & Panchanathan, S. (2002). A method for evaluating the performance of content-based image retrieval systems. In Proceedings - 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002 (Vol. 2002-January, pp. 96-100). [999897] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IAI.2002.999897

A method for evaluating the performance of content-based image retrieval systems. / Black, J. A.; Fahmy, G.; Panchanathan, Sethuraman.

Proceedings - 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002. Vol. 2002-January Institute of Electrical and Electronics Engineers Inc., 2002. p. 96-100 999897.

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

Black, JA, Fahmy, G & Panchanathan, S 2002, A method for evaluating the performance of content-based image retrieval systems. in Proceedings - 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002. vol. 2002-January, 999897, Institute of Electrical and Electronics Engineers Inc., pp. 96-100, 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002, Santa Fe, United States, 4/7/02. https://doi.org/10.1109/IAI.2002.999897
Black JA, Fahmy G, Panchanathan S. A method for evaluating the performance of content-based image retrieval systems. In Proceedings - 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002. Vol. 2002-January. Institute of Electrical and Electronics Engineers Inc. 2002. p. 96-100. 999897 https://doi.org/10.1109/IAI.2002.999897
Black, J. A. ; Fahmy, G. ; Panchanathan, Sethuraman. / A method for evaluating the performance of content-based image retrieval systems. Proceedings - 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002. Vol. 2002-January Institute of Electrical and Electronics Engineers Inc., 2002. pp. 96-100
@inproceedings{bac9aa89bf514f7bb5cad29e97ad83ab,
title = "A method for evaluating the performance of content-based image retrieval systems",
abstract = "In recent years multimedia researchers have attempted to design content-based image retrieval systems. However, despite the development of these systems, the term {"}content{"} has still remained rather ill defined, and this has made the evaluation of such systems problematic. This paper proposes a method for the creation of a test set of images in which the similarity of each image pair is estimated by two independent methods - by the subjective evaluation of human observers, and by the use of {"}content words{"} as basis vectors that allow the multidimensional content of each image to be represented with a content vector. The latter method is shown to correlate with the subjective judgement of human observers, and thus provide both a more objective method for evaluating and expressing image content, and a possible path to automating the process in the future.",
keywords = "Character recognition, Content based retrieval, Humans, Image databases, Image retrieval, Multimedia databases, Multimedia systems, Pattern recognition, Raw materials, Testing",
author = "Black, {J. A.} and G. Fahmy and Sethuraman Panchanathan",
year = "2002",
doi = "10.1109/IAI.2002.999897",
language = "English (US)",
volume = "2002-January",
pages = "96--100",
booktitle = "Proceedings - 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - A method for evaluating the performance of content-based image retrieval systems

AU - Black, J. A.

AU - Fahmy, G.

AU - Panchanathan, Sethuraman

PY - 2002

Y1 - 2002

N2 - In recent years multimedia researchers have attempted to design content-based image retrieval systems. However, despite the development of these systems, the term "content" has still remained rather ill defined, and this has made the evaluation of such systems problematic. This paper proposes a method for the creation of a test set of images in which the similarity of each image pair is estimated by two independent methods - by the subjective evaluation of human observers, and by the use of "content words" as basis vectors that allow the multidimensional content of each image to be represented with a content vector. The latter method is shown to correlate with the subjective judgement of human observers, and thus provide both a more objective method for evaluating and expressing image content, and a possible path to automating the process in the future.

AB - In recent years multimedia researchers have attempted to design content-based image retrieval systems. However, despite the development of these systems, the term "content" has still remained rather ill defined, and this has made the evaluation of such systems problematic. This paper proposes a method for the creation of a test set of images in which the similarity of each image pair is estimated by two independent methods - by the subjective evaluation of human observers, and by the use of "content words" as basis vectors that allow the multidimensional content of each image to be represented with a content vector. The latter method is shown to correlate with the subjective judgement of human observers, and thus provide both a more objective method for evaluating and expressing image content, and a possible path to automating the process in the future.

KW - Character recognition

KW - Content based retrieval

KW - Humans

KW - Image databases

KW - Image retrieval

KW - Multimedia databases

KW - Multimedia systems

KW - Pattern recognition

KW - Raw materials

KW - Testing

UR - http://www.scopus.com/inward/record.url?scp=8844226940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8844226940&partnerID=8YFLogxK

U2 - 10.1109/IAI.2002.999897

DO - 10.1109/IAI.2002.999897

M3 - Conference contribution

AN - SCOPUS:8844226940

VL - 2002-January

SP - 96

EP - 100

BT - Proceedings - 5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002

PB - Institute of Electrical and Electronics Engineers Inc.

ER -