Shading Removal of Illustrated Documents

  • Daniel Marques Oliveira
  • Rafael Dueire Lins
  • Gabriel de França Pereira e Silva
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7950)


Pictures of documents have non-uniform illumination causing shading which may yield to bad quality image for human visualization and unsuitable for some image processing algorithms. Most algorithms do not consider the scenario in which documents have large non-uniform regions such as photographs and illustrations. This paper proposes an algorithm to remove the shading of such documents. Once the background is identified, Natural Neighbor Interpolation estimates the shading for non-background pixels. The algorithm performed well on 33 synthetic images using SSIM and PSNR measures. The same quality of performance was confirmed in “real-world” images.


Shading removal Illumination normalization Enhancement 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Amidror, I.: Scattered data interpolation methods for electronic imaging systems: A survey. J. Electron. Imaging 11(2), 157–176 (2002)CrossRefGoogle Scholar
  2. 2.
    de Berg, M., et al.: Computational Geometry: Algorithms and Applications. Springer (2008)Google Scholar
  3. 3.
    Buchin, K., Mulzer, W.: Delaunay Triangulations in O(sort(n)) Time and More. In: 50th Annual IEEE Symposium on Foundations of Computer Science, pp. 139–148 (2009)Google Scholar
  4. 4.
    Fan, J.: Robust Color Image Enhancement of Digitized Books. In: Proceedings of 10th International Conference on Document Analysis and Recognition, pp. 561–565 (2009)Google Scholar
  5. 5.
    Flötotto, J.: 2D and Surface Function Interpolation. CGAL User and Reference Manual, CGAL Editorial Board, 3.8th edn. (2011)Google Scholar
  6. 6.
    Gatos, B., Pratikakis, I., Perantonis, S.J.: An Adaptive Binarization Technique for Low Quality Historical Documents. In: Marinai, S., Dengel, A.R. (eds.) DAS 2004. LNCS, vol. 3163, pp. 102–113. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  7. 7.
    Gatos, B., Pratikakis, I., Perantonis, S.J.: Adaptive degraded document image binarization. Pattern Recognition 39(3), 317–327 (2006)zbMATHCrossRefGoogle Scholar
  8. 8.
    Lins, R.D., Torreão, G., Pereira e Silva, G.: Content Recognition and Indexing in the liveMemory Platform. In: Ogier, J.-M., Liu, W., Lladós, J. (eds.) GREC 2009. LNCS, vol. 6020, pp. 220–230. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Niblack, W.: An Introduction to Digital Image Processing. Englewood Cliffs, New Jersey (1986)Google Scholar
  10. 10.
    Najaim & Aguiar Ltd. Negócios PE. 19th edn. Najaim & Aguiar Ltd., Recife (2011)Google Scholar
  11. 11.
    Najaim & Aguiar Ltd. Negócios PE, 18th edn. Najaim & Aguiar Ltd., Recife (2011)Google Scholar
  12. 12.
    Oliveira, D.M., Lins, R.D.: A New Method for Shading Removal and Binarization of Documents Acquired with Portable Digital Cameras. In: Third International Workshop on Camera-Based Document Analysis and Recognition, Barcelona, Spain, pp. 61–65 (2009)Google Scholar
  13. 13.
    Oliveira, D.M., Lins, R.D.: Generalizing Tableau to Any Color of Teaching Boards. In: 20th International Conference on Pattern Recognition, Istanbul, Turkey, pp. 2411–2414 (2010)Google Scholar
  14. 14.
    Sauvola, J., Pietikainen, M.: Adaptive document image binarization. Pattern Recognition 33(2) (2000)Google Scholar
  15. 15.
    Bukhari, S.S., Shafait, F., Breuel, T.M.: The IUPR Dataset of Camera-Captured Document Images. In: 4th Int. Workshop on Camera-Based Document Analysis and Recognition, Beijing, China (2011)Google Scholar
  16. 16.
    Lu, S., Tan, C.L.: Thresholding of badly illuminated document images through photometric correction. In: Proc. 2007 ACM Symp. Document Eng., Manitoba, Canada, pp. 3–8 (2007)Google Scholar
  17. 17.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing 13(4), 600–612 (2004), CrossRefGoogle Scholar
  18. 18.
    Zhang, L., Yip, A.M., Tan, C.L.: Photometric and geometric restoration of document images using inpainting and shape-from-shading. In: 22nd Conference on Artificial Intelligence, Vancouver, Canada, pp. 1121–1126 (2007)Google Scholar
  19. 19.
    Lee, J.-S., Chen, C.-H., Chang, C.-C.: A novel illumination-balance technique for improving the quality of degraded text-photo images. IEEE Trans. Cir. and Sys. for Video Technol. 19, 6 (2009)Google Scholar
  20. 20.
    Har-Peled, S.: Data structures for geometric approximation. American Mathematical Society (2011)Google Scholar
  21. 21.
    Eppstein, D.: Four levels of the Z curve, showing the square that is eventually filled by the curve, (last visited on March 20, 2013)
  22. 22.
    File, M.: Natural-neighbors-coefficients-example.png, (last visited on March 20, 2013)
  23. 23., (last visited on March 20, 2013)
  24. 24.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Prentice Hall, New Jersey (2008)Google Scholar
  25. 25.
    Athimethphat, M., Patanavijit, V.: A non-linear illuminations balancing for reconstructed degraded scanned text-photo image. In: ISCIT 2010, pp. 1158–1163 (2010), doi:10.1109/ISCIT.2010.5665163Google Scholar
  26. 26.
    Meng, G., Xiang, S., Zheng, N., Pan, C.: Non-parametric Illumination Correction for Scanned Document Images via Convex Hulls. IEEE Trans. on Pattern Ana. and Machine Intelligence (99)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Daniel Marques Oliveira
    • 1
  • Rafael Dueire Lins
    • 1
  • Gabriel de França Pereira e Silva
    • 1
    • 2
  1. 1.Universidade Federal de PernambucoRecifeBrazil
  2. 2.Universidade Federal Rural de PernambucoGaranhunsBrazil

Personalised recommendations