• DocumentCode
    1451568
  • Title

    Deformable template recognition of multiple occluded objects

  • Author

    Mardia, Kanti V. ; Qian, Wei ; Shah, Druti ; De Souza, Kevin M A

  • Author_Institution
    Dept. of Stat., Leeds Univ., UK
  • Volume
    19
  • Issue
    9
  • fYear
    1997
  • fDate
    9/1/1997 12:00:00 AM
  • Firstpage
    1035
  • Lastpage
    1042
  • Abstract
    Based on deformable templates, the paper formulates an integrated and flexible Bayesian recognition system of multiple occluded objects. Various local dependence properties of the model are obtained to reduce the computational cost with the increase in the number of objects. Numerical results for a synthetic image and for a real image of mushrooms are discussed
  • Keywords
    Bayes methods; computational complexity; image recognition; object recognition; computational cost; deformable template recognition; integrated flexible Bayesian recognition system; local dependence properties; multiple occluded objects; mushrooms; numerical results; Bayesian methods; Computational efficiency; Computational geometry; Deformable models; Iterative methods; Knowledge based systems; Markov random fields; Object recognition; Robots; Stochastic processes;
  • fLanguage
    English
  • Journal_Title
    Pattern Analysis and Machine Intelligence, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0162-8828
  • Type

    jour

  • DOI
    10.1109/34.615452
  • Filename
    615452