• DocumentCode
    281019
  • Title

    Artificial intelligence techniques for the automated analysis of ultrasonic NDT data

  • Author

    McNab, A. ; Dunlop, Iain

  • fYear
    1990
  • fDate
    33211
  • Firstpage
    42522
  • Lastpage
    42529
  • Abstract
    The following methods of NDT data processing techniques are considered: removal of noisy or spurious indications; derivation of missing indications; smoothing; thresholding; edge detection and flood-filling; and contouring. Classification of suspect regions and shape recognition are discussed. The following types of automated recognition techniques are considered: best-fit analysis; and triangulation analysis
  • fLanguage
    English
  • Publisher
    iet
  • Conference_Titel
    Advances in Transducers, Equipment and Data Processing to Improve the Reliability of NDT, IEE Colloquium on
  • Conference_Location
    London
  • Type

    conf

  • Filename
    193340