• DocumentCode
    2024187
  • Title

    Recognition of Chinese character in snapshot translation system

  • Author

    Wong, Fai ; Chao, Sam ; Chan, Wai Kit ; Li, Yi Ping

  • Author_Institution
    Fac. of Sci. & Technol., Univ. of Macau, Macau, China
  • fYear
    2010
  • fDate
    23-25 Nov. 2010
  • Firstpage
    821
  • Lastpage
    825
  • Abstract
    In this paper, we presents a mobile based snapshot translation system, Cyclops. The system takes an image of Chinese text as its input and translates the textual content of the image into either Portuguese or English, or both. The underneath design idea is to provide user a comprehensive user interface in using language translation tool to access the meaning of non-native text. The system has been developed based on different technologies including image processing, Chinese optical character recognition and machine translation. In this article, we focus on describing the character recognition module which uses Peripheral Direction Contributivity (PDC) for representing the features of Chinese character. Most importantly, it has been tailored to run on common use mobile devices which have memory and storage limitations.
  • Keywords
    image processing; language translation; optical character recognition; Chinese character recognition; Chinese optical character recognition; Chinese text; Cyclops; English; Portuguese; character recognition module; comprehensive user interface; image processing; language translation tool; machine translation; peripheral direction contributivity; snapshot translation system; Character recognition; Digital cameras; Mobile handsets; Optical character recognition software; Support vector machine classification; Table lookup; Text recognition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Audio Language and Image Processing (ICALIP), 2010 International Conference on
  • Conference_Location
    Shanghai
  • Print_ISBN
    978-1-4244-5856-1
  • Type

    conf

  • DOI
    10.1109/ICALIP.2010.5685132
  • Filename
    5685132