Scientific article
Open access

Statistical structuring of pictorial databases for content-based image retrieval systems

Published inPattern recognition letters, vol. 17, no. 12, p. 1299-1310
Publication date1996

This letter presents a two-stage statistical approach for ``exploring and explaining'' a pictorial database, for content-based image retrieval systems. First, we describe how correspondence analysis provides images classes, as well as facilitates the understanding of the role of image primatives and attributes used to index pictures. Such understanding allows an intelligent choice of features, and thus computational savings, to be made. Second, ascendant heirarchical classification permits the structuring of the database, in order to ease picture indexing and retrieval.

  • Image databases
  • Content-based image retrieval systems
  • Exploratory statistics
  • Correspondence analysis
  • Ascendant hierarchical classification
Citation (ISO format)
PUN, Thierry, SQUIRE, David. Statistical structuring of pictorial databases for content-based image retrieval systems. In: Pattern recognition letters, 1996, vol. 17, n° 12, p. 1299–1310. doi: 10.1016/0167-8655(96)84923-3
Main files (1)
Article (Published version)
ISSN of the journal0167-8655

Technical informations

Creation03/03/2015 4:36:15 PM
First validation03/03/2015 4:36:15 PM
Update time03/14/2023 10:57:10 PM
Status update03/14/2023 10:57:09 PM
Last indexation01/16/2024 5:03:49 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack