Content-Based Image Retrieval Using Combined 2D Attribute Pattern Spectra

Florence Tushabe*, Michael. H.F. Wilkinson

*Corresponding author for this work

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

11 Citations (Scopus)
379 Downloads (Pure)

Abstract

This work proposes a region-based shape signature that uses a combination of three different types of pattern spectra. The proposed method is inspired by the connected shape filter proposed by Urbach et al. We extract pattern spectra from the red, green and blue color bands of an image then incorporate machine learning techniques for application in photographic image retrieval. Our experiments show that the combined pattern spectrum gives an improvement of approximately 30% in terms of mean average precision and precision at 20 with respect to Urbach et al’s method.
Original languageEnglish
Title of host publicationADVANCES IN MULTILINGUAL AND MULTIMODAL INFORMATION RETRIEVAL
EditorsC Peters, Jikoun, T Mandl, H Muller, DW Oard, A Penas, Petras, D Santos
Place of PublicationBERLIN
PublisherUniversity of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science
Pages554-561
Number of pages8
ISBN (Print)978-3-540-85759-4
Publication statusPublished - 2008
Event8th Workshop of the Cross-Language Evaluation Forum - , Hungary
Duration: 19-Sep-200721-Sep-2007

Publication series

NameLECTURE NOTES IN COMPUTER SCIENCE
PublisherSPRINGER-VERLAG BERLIN
Volume5152
ISSN (Print)0302-9743

Other

Other8th Workshop of the Cross-Language Evaluation Forum
CountryHungary
Period19/09/200721/09/2007

Keywords

  • OPENINGS

Cite this