• DocumentCode
    2464259
  • Title

    Adding scale to the primal sketch

  • Author

    Saund, Eric

  • Author_Institution
    Dept. of Brain & Cognitive Sci., MIT, Cambridge, MA, USA
  • fYear
    1989
  • fDate
    4-8 Jun 1989
  • Firstpage
    70
  • Lastpage
    78
  • Abstract
    The author shows how a scale dimension can be added to Marr´s (1976) primal sketch to facilitate construction of multiscale descriptions of two-dimensional scales. In contrast to conventional scale-space approaches, this method omits any smoothing or blurring and performs grouping operations on symbolic shape tokens residing in a scale-space blackboard data structure. Two types of grouping operation are introduced: (1) fine-to-coarse aggregation of primitive-edge tokens builds coarser-scale edge maps from finer-scale information; and (2) pairwise grouping of symmetrically placed primitive edges gives rise to a primitive partial region token denoting curved-contour, primitive-corner, and bar events. The resulting collection of tokens makes the fundamental edge and region components of a shape´s geometry available to later symbolic processes, leading to shape recognition or other tasks
  • Keywords
    computerised pattern recognition; computerised picture processing; data structures; 2D scales; Marr´s primal sketch; bar events; computerised picture processing; curved-contour; feature extraction; fine-to-coarse aggregation; grouping operations; multiscale descriptions; pattern recognition; primitive-corner; primitive-edge tokens; scale dimension; scale-space blackboard data structure; shape recognition; symbolic shape tokens; Artificial intelligence; Data structures; Geometry; Image converters; Laboratories; Large-scale systems; Shape measurement; Smoothing methods; Tail; Visual system;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89., IEEE Computer Society Conference on
  • Conference_Location
    San Diego, CA
  • ISSN
    1063-6919
  • Print_ISBN
    0-8186-1952-x
  • Type

    conf

  • DOI
    10.1109/CVPR.1989.37830
  • Filename
    37830