• DocumentCode
    2988073
  • Title

    An Approach of Key Frame Extraction Based on Mutual Information

  • Author

    Huang, Lan-ying

  • Author_Institution
    Dept. of Comput. Sci., Xiaogan Univ., Xiaogan, China
  • fYear
    2009
  • fDate
    18-20 Jan. 2009
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    Key frame extraction is one of fundamental processes in video analysis and content-based video retrieval. Key frame can dramatically reduce the data of the video indexing, and provides a framework for video abstraction and retrieval. This paper briefly discusses the existing approaches, It presents a new approach for key frame extraction based on mutual information. Experimental results show that the approach is computationally simple and able to adapt to the visual content.
  • Keywords
    content-based retrieval; feature extraction; video retrieval; content-based video retrieval; key frame extraction; mutual information; video abstraction; video analysis; video indexing; visual content; Content based retrieval; Data mining; Density measurement; Entropy; Equations; Information analysis; Information retrieval; Layout; Mutual information; Random variables;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Network and Multimedia Technology, 2009. CNMT 2009. International Symposium on
  • Conference_Location
    Wuhan
  • Print_ISBN
    978-1-4244-5272-9
  • Type

    conf

  • DOI
    10.1109/CNMT.2009.5374631
  • Filename
    5374631