• DocumentCode
    3383704
  • Title

    The distributed, partial, and conditional Karhunen-Loeve transforms

  • Author

    Gastpar, Michael ; Dragotti, Pier-Luigi ; Vetterli, Martin

  • Author_Institution
    Dept. of EECS, California Univ., Berkeley, CA, USA
  • fYear
    2003
  • fDate
    25-27 March 2003
  • Firstpage
    283
  • Lastpage
    292
  • Abstract
    The Karhunen-Loeve transform (KLT) is a key element of many signal processing tasks, including approximation, compression, and classification. Many recent applications involve distributed signal processing where it is not generally possible to apply the KLT to the signal; the KLT must be approximated in a distributed fashion. Investigations were carried out on the distributed approximations to the KLT. First, explicit solutions to special cases were presented including a partial KLT, a conditional KLT, and the combination of these two special cases. These results were used to derive an algorithm that finds the best distributed approximation to the KLT. Applications of the results from sensor networks and distributed databases were discussed.
  • Keywords
    Karhunen-Loeve transforms; approximation theory; data compression; signal processing; Karhunen-Loeve transform; conditional KLT; distributed KLT; distributed databases; distributed signal processing; partial KLT; sensor networks; side information; signal approximation; signal classification; signal compression; signal processing tasks; source subset; Approximation algorithms; Cameras; Data compression; Decoding; Distributed databases; Educational institutions; Karhunen-Loeve transforms; Layout; Signal processing; Signal processing algorithms;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Data Compression Conference, 2003. Proceedings. DCC 2003
  • ISSN
    1068-0314
  • Print_ISBN
    0-7695-1896-6
  • Type

    conf

  • DOI
    10.1109/DCC.2003.1194019
  • Filename
    1194019