• DocumentCode
    3141549
  • Title

    Script line separation from Indian multi-script documents

  • Author

    Pal, U. ; Chaudhuri, B.B.

  • Author_Institution
    Comput. Vision & Pattern Recognition Unit, Indian Stat. Inst., Calcutta, India
  • fYear
    1999
  • fDate
    20-22 Sep 1999
  • Firstpage
    406
  • Lastpage
    409
  • Abstract
    In a multi-lingual country like India, a document page may contain more than one script form. Under the three-language formula, the document may be printed in English, Devnagari and one of the other official Indian languages. For OCR of such a document page, it is necessary to separate these three script forms before feeding them to the OCRs of individual scripts. In this paper, an automatic technique of separating the text lines using script characteristics and shape based features is presented. At present, the system has an overall accuracy of about 98.5%
  • Keywords
    document image processing; image segmentation; optical character recognition; Devnagari; English; Indian languages; Indian multi-script documents; OCR; document page; script form; script line separation; shape based features; text lines; three-language formula; Character generation; Computer vision; Natural languages; Optical character recognition software; Optical filters; Pattern recognition; Read only memory; Shape; Writing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on
  • Conference_Location
    Bangalore
  • Print_ISBN
    0-7695-0318-7
  • Type

    conf

  • DOI
    10.1109/ICDAR.1999.791810
  • Filename
    791810