Using efficient visual exploration techniques to evaluate features for content-based image retrieval

J. F. Rodrigues, C. A.B. Castañón, C. Traina, A. J.M. Traina

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

We present a novel visual approach to evaluate, in a fast and effective way, the development of new image feature extraction techniques concerning content-based image retrieval. This new approach takes advantage of an interactive 3-dimensional visualization fed by the image features obtained through a given extraction technique under analysis. Using controlled test image datasets, the researcher can literally "see" the discrimination power of the image features. This new approach gives a very good insight of the behavior of a given image feature extractor algorithm, which are confirmed by the well-known precision and recall measurements. We applied the visual approach proposed onto a wavelet-based image retrieval system, which is supporting the development of a Picture Archiving and Communication System that allows one to retrieve images by content.

Original languageEnglish
Title of host publicationProceedings - 16th Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2003
EditorsMaria Cristina Ferreira de Oliveira, Roberto Marcondes Cesar
PublisherIEEE Computer Society
Pages183-190
Number of pages8
ISBN (Electronic)0769520324
DOIs
StatePublished - 2003
Externally publishedYes
Event16th Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2003 - Sao Carlos, Brazil
Duration: 12 Oct 200315 Oct 2003

Publication series

NameBrazilian Symposium of Computer Graphic and Image Processing
Volume2003-January
ISSN (Print)1530-1834

Conference

Conference16th Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2003
Country/TerritoryBrazil
CitySao Carlos
Period12/10/0315/10/03

Keywords

  • Biomedical imaging
  • Content based retrieval
  • Feature extraction
  • Humans
  • Image retrieval
  • Indexing
  • Information retrieval
  • Medical diagnostic imaging
  • Picture archiving and communication systems
  • Testing

Fingerprint

Dive into the research topics of 'Using efficient visual exploration techniques to evaluate features for content-based image retrieval'. Together they form a unique fingerprint.

Cite this