• DocumentCode
    3494155
  • Title

    Symbolic representation of Kannada characters for recognition

  • Author

    Vikram, N.T. ; Gowda, K. Chidananda ; Urs, Shalini R.

  • Author_Institution
    Int. Sch. of Inf. Manage., Mysore
  • fYear
    2008
  • fDate
    6-8 April 2008
  • Firstpage
    823
  • Lastpage
    826
  • Abstract
    Kannada is a south Indian language, and one of the official languages of India. In this paper we propose a novel character representation scheme based symbolic data analysis, with Kannada as a case study. Symbolic data analysis (SDA) is a new domain in data management and knowledge discovery. SDA based methods have not been exploited for OCR of now. The proposed representation scheme is efficient in capturing the variations in font style and invariant to size. We also propose a similarity measure for recognition purpose.
  • Keywords
    data analysis; natural language processing; optical character recognition; Kannada character recognition; OCR; south Indian language; symbolic data analysis; symbolic representation; Character recognition; Data analysis; Discrete cosine transforms; Image segmentation; Knowledge management; Optical character recognition software; Pattern recognition; Principal component analysis; Support vector machine classification; Support vector machines;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on
  • Conference_Location
    Sanya
  • Print_ISBN
    978-1-4244-1685-1
  • Electronic_ISBN
    978-1-4244-1686-8
  • Type

    conf

  • DOI
    10.1109/ICNSC.2008.4525329
  • Filename
    4525329