• DocumentCode
    1567081
  • Title

    Skew detection of document images using line structural information

  • Author

    Kao, Chih-Hong ; Don, Hon-Son

  • Author_Institution
    Dept. of Electr. Eng., Nat. Chung-Hsing Univ., Taichung, Taiwan
  • Volume
    1
  • fYear
    2005
  • Firstpage
    704
  • Abstract
    A method for skew detection of document images is presented. The method is based on the information of the directions of text lines in the images. To extract the directions of text lines in the images, a measure of line-likeness of texts is adopted, which reflects the strength and direction of a pixel being part of a text line. This measure is applicable to texts of various fonts, sizes, and even languages. The skew angle of the whole image is the consensus among all pixels in the image. Several methods for the consensus are proposed. Experimental results of the method on document images are presented.
  • Keywords
    character recognition; document image processing; image recognition; document images; line structural information; skew detection; text line-likeness; Character recognition; Data mining; Histograms; Image analysis; Image enhancement; Image segmentation; Performance analysis; Pixel; Size measurement; Text analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Technology and Applications, 2005. ICITA 2005. Third International Conference on
  • Print_ISBN
    0-7695-2316-1
  • Type

    conf

  • DOI
    10.1109/ICITA.2005.255
  • Filename
    1488891