• DocumentCode
    521679
  • Title

    Recognition Research on Visual Invariants Using Conformal Geometric Algebra

  • Author

    Wang Xian ; Hao Kuang-Rong

  • Author_Institution
    Coll. of Inf. Sci. & Technol., Donghua Univ., Shanghai, China
  • fYear
    2010
  • fDate
    19-21 June 2010
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    This article firstly introduces the theory of conformal geometric algebra, the expression and calculation of geometry invariants are given by using this theory; the invariants of five-line structure are used as the features of detected target, the straight lines are extracted with the help of Hough transform and then matched directly by using the invariants of five-line structure. Target structure constraints are added in order to remove false matches. The method requires a small amount of computation and the simulation result proves its validity and rapidity.
  • Keywords
    Hough transforms; linear algebra; object detection; Hough transform; conformal geometric algebra; five line structure invariants; geometry invariants; visual invariants; Algebra; Application software; Computational modeling; Computer vision; Educational institutions; End effectors; Geometry; Layout; Object recognition; Textile technology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Photonics and Optoelectronic (SOPO), 2010 Symposium on
  • Conference_Location
    Chengdu
  • Print_ISBN
    978-1-4244-4963-7
  • Electronic_ISBN
    978-1-4244-4964-4
  • Type

    conf

  • DOI
    10.1109/SOPO.2010.5504339
  • Filename
    5504339