• DocumentCode
    2832830
  • Title

    Printed Thai character recognition using the hierarchical cross-correlation ARTMAP

  • Author

    Thammano, Arit ; Duangphasuk, Pruegsa

  • Author_Institution
    Fac. of Inf. Technol., King Mongkut´´s Inst. of Technol. Ladkrabang, Bangkok
  • fYear
    2005
  • fDate
    16-16 Nov. 2005
  • Lastpage
    698
  • Abstract
    Traditionally, Thai characters are composed of circle, zigzag line, curve, and head. However, many new Thai fonts, which are now gaining in popularity, do not follow the traditional writing rule; the head has been omitted from the characters. Without the head, it is very difficult to segregate the characters. Even the best commercial Thai OCR software has difficulty in recognizing this kind of character. Therefore, the hierarchical cross-correlation ARTMAP is proposed in this paper to recognize the no-head Thai characters
  • Keywords
    character recognition; correlation methods; natural languages; hierarchical cross-correlation ARTMAP; printed Thai character recognition; Character recognition; Feature extraction; Feedforward neural networks; Head; Image segmentation; Information technology; Natural languages; Neural networks; Optical character recognition software; Writing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Tools with Artificial Intelligence, 2005. ICTAI 05. 17th IEEE International Conference on
  • Conference_Location
    Hong Kong
  • ISSN
    1082-3409
  • Print_ISBN
    0-7695-2488-5
  • Type

    conf

  • DOI
    10.1109/ICTAI.2005.100
  • Filename
    1563021