• DocumentCode
    2558673
  • Title

    A new method of point clouds extraction from the 3D volume data

  • Author

    Wang, Zhaofeng ; Yan, Bin ; Li, Jianxin ; Tong, Li ; Chen, Jian

  • Author_Institution
    China Nat. Digital Switching Syst. Eng. & Technol. Res. Center(NDSC), Zhengzhou, China
  • fYear
    2012
  • fDate
    29-31 May 2012
  • Firstpage
    362
  • Lastpage
    365
  • Abstract
    The point clouds is an important kind of three-dimensional data expression form. In the 3D point-based rendering and reverse engineering, it acts as an irreplaceable role. In this paper, the volume data was preprocessed and broken down into a series of 2D slices for contours extraction, finally all of the points extracted were inputted into self-organized network for cluster analysis. The feasibility of this method was proved in both theory and practice. The approach may be taken as a useful reference for researchers working on extracting point clouds from volume data.
  • Keywords
    feature extraction; pattern clustering; rendering (computer graphics); reverse engineering; self-organising feature maps; solid modelling; 2D slices; 3D point-based rendering; 3D volume data; SOM; cluster analysis; contour extraction; neural network; point clouds extraction; reverse engineering; self-organized mapping; self-organized network; three-dimensional data expression form; Algorithm design and analysis; Computed tomography; Data mining; Neurons; Rendering (computer graphics); Shape; Vectors; Neural Network; Point Clouds Extraction; Self-Organized Mapping(SOM); Volume Data;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Natural Computation (ICNC), 2012 Eighth International Conference on
  • Conference_Location
    Chongqing
  • ISSN
    2157-9555
  • Print_ISBN
    978-1-4577-2130-4
  • Type

    conf

  • DOI
    10.1109/ICNC.2012.6234642
  • Filename
    6234642