Search and Progressive Information Retrieval From Distributed Image/Video Databases: The SPIRE Project

  • Vittorio Castelli
  • Lawrence D. Bergman
  • Chung-Sheng Li
  • John R. Smith
Conference paper

DOI: 10.1007/3-540-49653-X_10

Part of the Lecture Notes in Computer Science book series (LNCS, volume 1513)
Cite this paper as:
Castelli V., Bergman L.D., Li CS., Smith J.R. (1998) Search and Progressive Information Retrieval From Distributed Image/Video Databases: The SPIRE Project. In: Research and Advanced Technology for Digital Libraries. ECDL 1998. Lecture Notes in Computer Science, vol 1513. Springer, Berlin, Heidelberg

Abstract

In this paper, we describe the architecture and initial implementation of a content-based retrieval mechanism from heterogeneous image archives. In particular, we propose an architecture to produce local representation of the images stored in heterogeneous archives and a progressive framework that reorganizes the images into a hierarchical representation based on a multiresolution decomposition and an abstraction pyramid. Search operations can rely on this representation and be performed in a hierarchical fashion, thus significantly reducing the total amount of data that need to be processed. Dramatic speedup has been achieved for many search operations, such as template matching, texture feature extraction, and histogram extraction.

Keywords

image databases satellite imagery content-based retrieval 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-VerlagBerlin Heidelberg 1998

Authors and Affiliations

  • Vittorio Castelli
    • 1
  • Lawrence D. Bergman
    • 1
  • Chung-Sheng Li
    • 1
  • John R. Smith
    • 1
  1. 1.IBM Thomas J. Watson Research CenterYorktown Heights

Personalised recommendations