• DocumentCode
    3022405
  • Title

    Extraction of specified objects from binary images using object based erosion transform: application to Hebrew calligraphic manuscripts

  • Author

    Bar-Yosef, Itay ; Beckman, Isaac ; Kedem, Klara ; Dinstein, Itshak

  • Author_Institution
    Dept. of Comput. Sci., Ben-Gurion Univ., Israel
  • fYear
    2005
  • fDate
    29 Aug.-1 Sept. 2005
  • Firstpage
    878
  • Abstract
    This paper presents a method for automatic extraction of certain pre-specified objects from binary images. The method is applied to letters from historic Hebrew manuscripts and is based on object based erosion transform. The extraction method deals very well with common problems of historical documents, such as broken or merged characters, and can be applied to different writing styles. An average correct extraction rate of 96% is achieved.
  • Keywords
    document image processing; feature extraction; humanities; natural languages; transforms; Hebrew calligraphic manuscript; binary image; historical document; object based erosion transform; object extraction; writing style; Application software; Computer science; Content based retrieval; Degradation; Image retrieval; Image segmentation; Morphology; Shape; Text recognition; Writing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on
  • ISSN
    1520-5263
  • Print_ISBN
    0-7695-2420-6
  • Type

    conf

  • DOI
    10.1109/ICDAR.2005.108
  • Filename
    1575670