• DocumentCode
    1075522
  • Title

    Asymmetrical principal component analysis for video coding

  • Author

    Söderström, U. ; Li, H.

  • Author_Institution
    Umed Univ., Umed
  • Volume
    44
  • Issue
    4
  • fYear
    2008
  • Firstpage
    276
  • Lastpage
    277
  • Abstract
    Principal component analysis (PCA) can be used to encode video sequences at extremely low bit rates, e.g. 34.6 dB (PSNR) at 4.2 kbit/s. The same eigenvectors are used for encoding and decoding for this coding. Introduced is a coding scheme where eigenvectors for only part of the video frames are used for encoding but the eigenvectors for the entire frame are used for decoding. This is called asymmetric PCA coding. This reduces the complexity of encoding by ap5 times and at the same time increases the reconstruction quality for the facial part of the video with 0.4 dB (PSNR)..
  • Keywords
    decoding; eigenvalues and eigenfunctions; image sequences; principal component analysis; video coding; asymmetric PCA coding; decoding; eigenvectors; encoding; principal component analysis; video coding; video frames; video sequences;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:20083631
  • Filename
    4455405