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

9 Scopus citations

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
ISBN (Electronic)0769515371
DOIs
StatePublished - Jan 1 2002
Event5th IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2002 - Santa Fe, United States
Duration: Apr 7 2002Apr 9 2002

Publication series

NameProceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Volume2002-January

Other

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

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

Fingerprint

Dive into the research topics of 'A method for evaluating the performance of content-based image retrieval systems'. Together they form a unique fingerprint.

Cite this