• DocumentCode
    588773
  • Title

    Research on the Technology of Video Key Frame Extraction Based on Clustering

  • Author

    Zhonglan Wu ; Pin Xu

  • Author_Institution
    Commun. Univ. of China, Beijing, China
  • fYear
    2012
  • fDate
    2-4 Nov. 2012
  • Firstpage
    290
  • Lastpage
    293
  • Abstract
    The video key frame extraction technology is one of the important parts of content-based video retrieval. And the mainstream of key frame extraction is the algorithm based on clustering. The basic idea is: the video frames are grouped in accordance with the correlation of the visual content by clustering, and then we extract the most representative frame from each group as a key frame. In this paper, several common key frame extraction algorithms based on clustering are elaborated along with their advantages and disadvantages.
  • Keywords
    content-based retrieval; pattern clustering; video retrieval; clustering; content-based video retrieval; representative frame extraction; video key frame extraction technology; visual content; Clustering algorithms; Data mining; Feature extraction; Histograms; Image color analysis; Vectors; Visualization; clustering; key frame; video abstract;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multimedia Information Networking and Security (MINES), 2012 Fourth International Conference on
  • Conference_Location
    Nanjing
  • Print_ISBN
    978-1-4673-3093-0
  • Type

    conf

  • DOI
    10.1109/MINES.2012.190
  • Filename
    6405681