• DocumentCode
    1744971
  • Title

    On the performance of CNNs for associative memories in robot vision systems

  • Author

    Brucoli, Michele ; Cafagna, Donato ; Carnimeo, Leonavda

  • Author_Institution
    Dipartimento di Elettrotecnica ed Elettronica, Politecnico di Bari, Italy
  • Volume
    3
  • fYear
    2001
  • fDate
    6-9 May 2001
  • Firstpage
    341
  • Abstract
    In this paper a DTCNN-based vision system for pattern recognition in an artificial vision architecture is illustrated. The bipolar images, segmented in a preprocessing stage, constitute the input to a cellular associative memory in the recognizing stage of the vision system. The performance of DTCNNs designed as associative memories is confirmed by means of examples of detection and recognition of tools handled by a robot in an assembly line
  • Keywords
    cellular neural nets; content-addressable storage; image segmentation; industrial robots; pattern recognition; robot vision; assembly line; associative memory; bipolar image segmentation; discrete time cellular neural network; pattern recognition; robot vision system; tool detection; Associative memory; Belts; Cellular neural networks; Data preprocessing; Image processing; Image segmentation; Machine vision; Object detection; Robot vision systems; Robotic assembly;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE International Symposium on
  • Conference_Location
    Sydney, NSW
  • Print_ISBN
    0-7803-6685-9
  • Type

    conf

  • DOI
    10.1109/ISCAS.2001.921317
  • Filename
    921317