• DocumentCode
    1783109
  • Title

    The research of visual attention mechanism model fuse multi-feature

  • Author

    ZhenKun Wen ; YiHua Du ; HuiSi Wu ; Lei Wang

  • Author_Institution
    Coll. of Comput. Sci. & Software, Shenzhen Univ., Shenzhen, China
  • fYear
    2014
  • fDate
    28-29 Sept. 2014
  • Firstpage
    1
  • Lastpage
    7
  • Abstract
    With the rapid development of network technology and multimedia technology, the researchers found that the neurobiology of human vision, computer vision and image and video processing and efficient combination for image, video can provide a more good solution of content retrieval applications, on the one hand, the simulation and study of visual attention mechanisms, can accurate images, video scene division of the region; we analyze the current theoretical basis of mechanism model, Proposed a significant degree measure algorithm fused color significant information, density significant and frequency domain transform significant base on visual attention mechanism model focus on multi-feature integration. Make records of significant area combined with a significant figure and as foundation for subsequent research and work.
  • Keywords
    computer vision; feature extraction; image fusion; computer vision; content retrieval application; degree measure algorithm; density significant; frequency domain transform significant; fused color significant information; human vision; image processing; multifeature fusion; multifeature integration; multimedia technology; network technology; video processing; video scene division; visual attention mechanism model; Brightness; Computational modeling; Data models; Feature extraction; Gabor filters; Image color analysis; Visualization; Feature Fusion; Visual Attention;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multisensor Fusion and Information Integration for Intelligent Systems (MFI), 2014 International Conference on
  • Conference_Location
    Beijing
  • Print_ISBN
    978-1-4799-6731-5
  • Type

    conf

  • DOI
    10.1109/MFI.2014.6997692
  • Filename
    6997692