A New Image Binarization Technique by Classifying Document Images

  • Soumik Datta
  • Pawan Kumar Singh
  • Ram Sarkar
  • MitaNasipuri
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)

Abstract

The present work proposes a binarization algorithm based on classification of document images. The method first classifies the images into two categories namely, simple and complex images. The global threshold value is used for binarizing the simple document images whereas complex document images are binarized by applying local threshold values. A background checking method is introduced in this method to detect the blocks which can be marked as purely background blocks. Finally, a post-processing mechanism has been applied to improve the quality of the binarized image.

Keywords

Binarization Document image analysis Optical Character Recognition Global Thresholding Local Thresholding Simple Document Images Complex Document Images 

References

  1. 1.
    Valizadeh, M., Armanfard, N., Komeili, M., Kabir, E.: A novel hybrid algorithm for binarization of badly illuminated document images. In: 14th International CSI Computer Conference (CSICC), pp. 121–126 (2009)Google Scholar
  2. 2.
    Kawano, H., Oohama, K., Maeda, H., Okada, Y., Ikoma: Degraded document image binarization combining local statistics. In: ICROS-SICE International Joint Conference, August 18-21 (2009)Google Scholar
  3. 3.
    Chang, Y.F., Pai, Y.T., Ruan, S.J.: An efficient thresholding algorithm for degraded document images based on intelligent block detection. In: IEEE Int. Conf. Syst. Man Cybern. SMC (2008)Google Scholar
  4. 4.
    Gatos, B., Pratikakis, I., Perantonis, S.J.: Efficient binarization of historical and degraded document images. In: The Eighth IAPR Workshop on Document Analysis Systems (2008)Google Scholar
  5. 5.
    Ostu, N.: A thresholding selection method from gray-level histogram. IEEE Trans. Systems Man Cybernet. SMC 8, 62–66 (1978)CrossRefGoogle Scholar
  6. 6.
    Kittler, J., Illingworth, J.: Minimum error thresholding. Pattern Recognition 19(1), 41–47 (1986)CrossRefGoogle Scholar
  7. 7.
    Bernsen, J.: Dynamic thresholding of gray-level images. In: Proc. Eighth International Conference on Pattern Recognition, Paris, pp. 1251–1125 (1986)Google Scholar
  8. 8.
    Niblack, W., Prentice, N.J., Cliffs, E.: An Introduction to Digital Image Processing (1986)Google Scholar
  9. 9.
    Sauvola, J., Pietikainen, M.: Adaptive Document Image Binarization. Pattern Recognition 33, 225–236 (2000)CrossRefGoogle Scholar
  10. 10.
    Su, B., Lu, S., Tan, C.L.: Combination of Document Image Binarization Techniques. In: International Conference on Document Analysis and Recognition (2011)Google Scholar
  11. 11.
    Shaikh, S.H., Maiti, A.K., Chaki, N.: A new image binarization method using iterative partitioning. Springer (2012) (published online: January 6, 2012)Google Scholar
  12. 12.
  13. 13.
  14. 14.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Soumik Datta
    • 1
  • Pawan Kumar Singh
    • 1
  • Ram Sarkar
    • 1
  • MitaNasipuri
    • 1
  1. 1.Department of Computer Science and EngineeringJadavpur UniversityKolkataIndia

Personalised recommendations