• DocumentCode
    285243
  • Title

    Recognitron-a neural net model for character recognition

  • Author

    Zurada, Jacek M. ; Jagiello, Krzysztof

  • Author_Institution
    Dept. of Electr. Eng., Louisville Univ., KY, USA
  • Volume
    3
  • fYear
    1992
  • fDate
    7-11 Jun 1992
  • Firstpage
    637
  • Abstract
    A neural network model called a recognitron is described. The recognitron uses a global mechanism for feature detection as compared to another net, called the neocognitron, which applied a local detection mechanism. The net consists of four layers and the output subnet. The Hamming net is used as the output subnet. The results of computer simulation of the recognitron are presented to show its ability for extracting and mapping features from noisy images of handwritten characters
  • Keywords
    character recognition; neural nets; Hamming net; character recognition; computer simulation; feature detection; feature extraction; feature mapping; global mechanism; handwritten characters; local detection mechanism; neural net model; noisy images; recognitron; Biological neural networks; Character recognition; Computer simulation; Computer vision; Data mining; Feature extraction; Image recognition; Neural networks; Neurons; Pattern recognition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1992. IJCNN., International Joint Conference on
  • Conference_Location
    Baltimore, MD
  • Print_ISBN
    0-7803-0559-0
  • Type

    conf

  • DOI
    10.1109/IJCNN.1992.227102
  • Filename
    227102