• DocumentCode
    2993951
  • Title

    Using perceptual grouping to recognize and locate partially occluded objects

  • Author

    Rearick, T.C. ; Frawley, J.L. ; Cortopassi, P.P.

  • Author_Institution
    Lockheed Aeronaut. Syst. Co., Marietta, GA, USA
  • fYear
    1988
  • fDate
    5-9 Jun 1988
  • Firstpage
    840
  • Lastpage
    846
  • Abstract
    The authors describe a connectionist network which is not a neural net in which knowledge is distributed globally via the connections of functionally simple nodes. The technique combines constraint propagation with analogical or eidetic representations. It represents an alternative to the atomistic signals-to-symbols paradigm in which a one-to-one correspondence is assumed to exist between symbols and the concepts they represent
  • Keywords
    artificial intelligence; knowledge engineering; pattern recognition; visual perception; artificial intelligence; connectionist network; constraint propagation; eidetic representations; knowledge engineering; partially occluded objects; pattern recognition; perceptual grouping; Computational modeling; Image recognition; Layout; Machine intelligence; Machine vision; Neural networks; Prototypes; Shape; Spatial resolution; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition, 1988. Proceedings CVPR '88., Computer Society Conference on
  • Conference_Location
    Ann Arbor, MI
  • ISSN
    1063-6919
  • Print_ISBN
    0-8186-0862-5
  • Type

    conf

  • DOI
    10.1109/CVPR.1988.196331
  • Filename
    196331