• DocumentCode
    2895614
  • Title

    A New Method for Line Segmentation of Handwritten Hindi Text

  • Author

    Garg, Naresh Kumar ; Kaur, Lakhwinder ; Jindal, M.K.

  • Author_Institution
    GZS Coll. of Eng. & Tech., Bathinda, India
  • fYear
    2010
  • fDate
    12-14 April 2010
  • Firstpage
    392
  • Lastpage
    397
  • Abstract
    In this paper, we have discussed the new method for Line Segmentation of Handwritten Hindi text. The method is based on header line detection, base line detection and contour following technique. No preprocessing like skew correction, thinning or noise removal has been done on the data. The purpose of this paper is three fold. Firstly, we explained by experiments that this method is suitable for fluctuating lines or variable skew lines of text. Also, we confirm that this method is invariant of non uniform skew between words in a line (non uniform text line skew). Secondly, the contour following after header line detection correctly separates some of the overlapped lines of text. Thirdly, this paper provides a brief review of text line segmentation techniques for handwritten text which can be very useful for the beginners who want to work on text line segmentation.
  • Keywords
    handwritten character recognition; image segmentation; natural language processing; text analysis; base line detection; handwritten Hindi text; header line detection; line segmentation; skew correction; Character recognition; Databases; Handwriting recognition; Information technology; Linear programming; Natural languages; Optical character recognition software; Pattern recognition; Text recognition; Writing; Text line segmentation; base line detection; contour following; header line; projection;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Technology: New Generations (ITNG), 2010 Seventh International Conference on
  • Conference_Location
    Las Vegas, NV
  • Print_ISBN
    978-1-4244-6270-4
  • Type

    conf

  • DOI
    10.1109/ITNG.2010.89
  • Filename
    5501694