Multimedia Tools and Applications

, Volume 4, Issue 2, pp 153–170

Supporting Content-Based Retrieval in Large Image Database Systems

  • Edward Remias
  • Gholamhosein Sheikholeslami
  • Aidong Zhang
  • Tanveer Fathima Syeda-Mahmood
Article

DOI: 10.1023/A:1009614331352

Cite this article as:
Remias, E., Sheikholeslami, G., Zhang, A. et al. Multimedia Tools and Applications (1997) 4: 153. doi:10.1023/A:1009614331352

Abstract

In this paper, we investigate approaches to supporting effective and efficient retrieval of image data based on content. We firstintroduce an effective block-oriented image decomposition structure which can be used to represent image content inimage database systems. We then discuss theapplication of this image data model to content-based image retrieval.Using wavelet transforms to extract image features,significant content features can be extracted from image datathrough decorrelating the data in their pixel format into frequency domain. Feature vectors ofimages can then be constructed. Content-based image retrievalis performed by comparing the feature vectors of the query imageand the decomposed segments in database images.Our experimental analysis illustrates that the proposed block-oriented image representationoffers a novel decomposition structure to be used tofacilitate effective and efficient image retrieval.

content-based image retrieval image database systems texture image decomposition image representation wavelet transforms 

Copyright information

© Kluwer Academic Publishers 1997

Authors and Affiliations

  • Edward Remias
    • 1
  • Gholamhosein Sheikholeslami
    • 2
  • Aidong Zhang
    • 2
  • Tanveer Fathima Syeda-Mahmood
    • 3
  1. 1.Department of Electrical and Computer EngineeringState University of New York at BuffaloBuffalo
  2. 2.Department of Computer ScienceState University of New York at BuffaloBuffalo
  3. 3.Xerox Research CenterWebster

Personalised recommendations