• DocumentCode
    2632064
  • Title

    A bar code location algorithm using a two-dimensional approach

  • Author

    Viard-Gaudin, Christian ; Normand, Nicolas ; Barba, Dominique

  • Author_Institution
    LATI/IRESTE-IUT de Nantes, France
  • fYear
    1993
  • fDate
    20-22 Oct 1993
  • Firstpage
    45
  • Lastpage
    48
  • Abstract
    Proposes a method for locating bar code blocks on parcels. One of the main difficulties involved is the combination of the very poor quality and the potential high complexity of the gray-level images. The image resolution has been chosen to be as low as possible in order to enlarge the field of view for a given number of CCD elements. Furthermore the focus of the camera has previously needed to be kept constant in spite of the variation in height of the objects resulting in the presence of high convolution distortion such that the width of the point spread function can be much larger than the width of a single stripe. The approach relies on the extraction of areas having a high density of mono-oriented gradient. This bar code finder algorithm works correctly for all images of a base provided by the French postal services
  • Keywords
    bar codes; feature extraction; image enhancement; image recognition; image resolution; postal services; 2D approach; CCD elements; French postal services; area extraction; bar code blocks; bar code location algorithm; camera focus; convolution distortion; gray-level images; image resolution; mono-oriented gradient; object height variability; parcels; point spread function; stripe width; Automation; Charge coupled devices; Charge-coupled image sensors; Convolution; Focusing; Humans; Image resolution; Machine vision; Optical character recognition software; Postal services;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on
  • Conference_Location
    Tsukuba Science City
  • Print_ISBN
    0-8186-4960-7
  • Type

    conf

  • DOI
    10.1109/ICDAR.1993.395785
  • Filename
    395785