Document analysis and graphics recognition algorithms are normally applied to the processing of images of 2D documents scanned when flattened against a planar surface. Technological advancements in recent years have led to a situation in which digital cameras with high resolution are widely available. Consequently, traditional graphics recognition tasks may be updated to accommodate document images captured through a hand-held camera in an uncontrolled environment. In this paper the problem of perspective and geometric deformations correction in document images is discussed. The proposed approach uses the texture of a document image so as to infer the document structure distortion. A two-pass image warping algorithm is then used to correct the images. In addition to being language independent, the proposed approach may handle document images that include multiple fonts, math notations, and graphics. The de-warped images contain less distortions and so are better suited for existing text/graphics recognition techniques.


perspective correction document de-warping document pre-processing graphics recognition document analysis image processing 


  1. 1.
    G. Agam. Perspective and geometric correction for graphics recognition. In Proc. GREC’01, pages 395–407, Kingston, Ontario, 2001.Google Scholar
  2. 2.
    A. Amin, S. Fischer, A.F. Parkinson, and R. Shiu. Comparative study of skew algorithms. Journal of Electronic Imaging, 5(4):443–451, 1996.CrossRefGoogle Scholar
  3. 3.
    H. Baird. Document image defect models. In Proc. SSPR’90, pages 38–46, 1990.Google Scholar
  4. 4.
    M.S. Brown and W.B. Seales. Document restoration using 3d shape: a general deskewing algorithm for arbitrarily warped documents. In Proc. ICCV’01, pages 367–374, Vancouver, BC, Jul. 2001. IEEE.Google Scholar
  5. 5.
    A. Doncescu, A. Bouju, and V. Quillet. Former books digital processing: image warping. In Proc. Workshop on Document Image Analysis, pages 5–9, San Juan, Puerto Rico, Jun. 1997.Google Scholar
  6. 6.
    David F. Rogers. Procedural elements for computer graphics. McGraw-Hill, second edition, 1998.Google Scholar
  7. 7.
    H. Fujisawa, H. Sako, Y. Okada, and S. Lee. Information capturing camera and developmental issues. In Proc. ICDAR’99, pages 205–208, 1999.Google Scholar
  8. 8.
    D.J. Ittner and H.S. Baird. Language-free layout analysis. In Proc. ICDAR’93, pages 336–340, Tsukuba, Japan, 1993.Google Scholar
  9. 9.
    T. Kanungo, R. Haralick, and I. Philips. Global and local document degradation models. In Proc. ICDAR’93, pages 730–734, 1993.Google Scholar
  10. 10.
    H. Li, D. Doermann, and O. Kia. Automatic text detection and tracking in digital video. IEEE Trans. Image Processing, 9(1):147–156, 2000.CrossRefGoogle Scholar
  11. 11.
    J. Sauvola, T. Seppanen, S. Haapakoski, and M. Pietikainen. Adaptive document binarization. In Proc. ICDAR’97, pages 147–152, Ulm, Germany, Aug. 1997.Google Scholar
  12. 12.
    M. Sawaki, H. Murase, and N. Hagita. Character recognition in bookshelf images by automatic template selection. In Proc. ICPR’98, pages 1117–1120, Aug. 1998.Google Scholar
  13. 13.
    M. Shridhar, J.W.V. Miller, G. Houle, and L. Bijnagte. Recognition of license plate images: issues and perspectives. In Proc. ICDAR’99, pages 17–20, 1999.Google Scholar
  14. 14.
    G. Worlberg. Digital Image Warping. IEEE Computer Society Press, Los Alamitos, California, 1990.Google Scholar
  15. 15.
    Z. Zhang and C.L. Tan. Recovery of distorted document images from bound volumes. In Proc. ICDAR’01, pages 429–433, Seattle, WA, 2001.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Changhua Wu
    • 1
  • Gady Agam
    • 1
  1. 1.Department of Computer ScienceIllinois Institute of TechnologyChicago

Personalised recommendations