• DocumentCode
    438868
  • Title

    Orthogonal ICA representation of images

  • Author

    Jin, Zhong ; Davoine, Franck

  • Author_Institution
    Centre de Visio per Computador, Univ. Autonoma de Barcelona, Spain
  • Volume
    1
  • fYear
    2004
  • fDate
    6-9 Dec. 2004
  • Firstpage
    369
  • Abstract
    Firstly, this paper answered one interesting question: what is orthogonal in ICA? We discussed the non-orthogonality of ICA transformation and claimed that the independent components (ICs) by the FastICA algorithm are orthogonal. Based on this orthogonality, an orthogonal ICA representation (OICA) of images was proposed. Experiments on ORL database, Yale database and CMU database with OICA were performed. More work is needed to discover any advantage of OICA.
  • Keywords
    image representation; independent component analysis; CMU database; FastICA algorithm; ORL database; Yale database; independent components; orthogonal ICA representation; Arm; Blind source separation; Covariance matrix; Face recognition; Image analysis; Image databases; Independent component analysis; Principal component analysis; Random variables; Vectors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Control, Automation, Robotics and Vision Conference, 2004. ICARCV 2004 8th
  • Print_ISBN
    0-7803-8653-1
  • Type

    conf

  • DOI
    10.1109/ICARCV.2004.1468853
  • Filename
    1468853