• DocumentCode
    2453227
  • Title

    Boundaries recognition and classification for slicing image of assembly

  • Author

    Feng, Yuqiang ; Hu, Yusheng

  • Author_Institution
    Sch. of Mech. Eng., Jimei Univ., Xiamen, China
  • fYear
    2010
  • fDate
    24-27 Aug. 2010
  • Firstpage
    81
  • Lastpage
    84
  • Abstract
    This paper presents an approach to recognize and classify the boundaries of assembly image. Its procedure includes: Step 1: By tracing, all contour rings are identified firstly, then using transformation algorithm, all non minimum contact rings are transformed to minimal contact rings; Step 2: A contour ring tree is constructed according to the relation of all rings; Step 3: Deformation is imposed to the tree by copying, inserting, uniting and deleting a node in the tree, the final ring tree completely and exactly expresses the inclusion relation of contour rings of assembly slice image; Step4: Classification is applied to the contour rings by material-region matching, continuity checking and combination. The entire contours of assembly can be correctly classified in order to reconstruct the geometric model of part in assembly.
  • Keywords
    edge detection; image classification; image reconstruction; trees (mathematics); assembly image boundaries classification; assembly slice image classification; boundaries recognition; contour ring tree; geometric model; inclusion relation; material region matching; minimal contact ring; transformation algorithm; tree deformation; tree node; Assembly; Image recognition; Image reconstruction; Image segmentation; Nickel; Solid modeling; Three dimensional displays; 3D Reconstruction; Assembly; Boundaries Classification; Boundaries Recognition; Slice images;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Science and Education (ICCSE), 2010 5th International Conference on
  • Conference_Location
    Hefei
  • Print_ISBN
    978-1-4244-6002-1
  • Type

    conf

  • DOI
    10.1109/ICCSE.2010.5593680
  • Filename
    5593680