• DocumentCode
    3085178
  • Title

    Global feature extraction of off-line Arabic handwriting

  • Author

    Touj, Sofien ; Ben Amara, Najoua ; Amiri, Hamid

  • Author_Institution
    Inst. Superieure des Etudes Technologiques de Gabes, Tunisia
  • Volume
    4
  • fYear
    2002
  • fDate
    6-9 Oct. 2002
  • Abstract
    We present the parameterisation stage of an off-line Arabic handwriting recognition system. The method is based on the Hough transform. This technique is well known for its robustness for detection of lines in images and for its capacity of absorption of distortions as well as noises that can blemish the script. We show through the obtained results the efficiency of this method for the extraction of the global features of Arabic letter tracing.
  • Keywords
    Hough transforms; document image processing; feature extraction; handwritten character recognition; optical character recognition; Arabic letter tracing; Hough transform; OCR; global feature extraction; line detection; noise; offline Arabic handwriting recognition system; parameterisation stage; Absorption; Data mining; Feature extraction; Handwriting recognition; Humans; Image edge detection; Noise robustness; Optical character recognition software; Shape; Writing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Systems, Man and Cybernetics, 2002 IEEE International Conference on
  • ISSN
    1062-922X
  • Print_ISBN
    0-7803-7437-1
  • Type

    conf

  • DOI
    10.1109/ICSMC.2002.1173264
  • Filename
    1173264