An Algorithm for Foreground-Background Separation in Low Quality Patrimonial Document Images

  • Carlos A. B. Mello
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)


In this article, we present a new algorithm to deal with foreground-background separation in very degraded documents. In particular, our work is applied to patrimonial document images which suffer from several types of degradation as aging effects, noise, back-to-front ink interference, etc. Our main objective is to correctly classify ink and paper to allow an efficient segmentation of the image creating high quality monochromatic images. This makes easier the broadcast of these images through the Internet. The new algorithm is based on the classical Shannon definition of entropy and a generalization defined as Tsallis Entropy and it is compared to 19 well-known classical algorithms, including DjVu algorithm. It achieved the best results by analyzing precision, recall, accuracy, specificity, PSNR and MSE.


Document processing Image thresholding Entropy 


  1. 1.
    Antonacopoulos, A., Castilla, C.C.: Flexible Text Recovery from Degraded Typewritten Historical Documents. In: Int. Conf. on Pattern Recognition, pp. 1062–1065, Japan (2006)Google Scholar
  2. 2.
    Bottou, L., Haffner, P., Howard, P.G.: High Quality Document Image Compression with DjVu. Journal of Electronic Imaging, 410–425 (1998),
  3. 3.
    Chen, Y., Leedham, G.: Decompose algorithm for thresholding degraded. Historical document images, Vision, Image and Signal Processing 152(6), 702–714 (2005)CrossRefGoogle Scholar
  4. 4.
    Kapur, J.N.: Measures of Information and their Applications. J.Wiley & Sons, Chichester (1994)zbMATHGoogle Scholar
  5. 5.
    Kavallieratou, E., Stamatatos, E.: Improving the Quality of Degraded Document Images, Int. Conf. on Document Image Analysis for Libraries, pp. 340–349, France (2006)Google Scholar
  6. 6.
    Kennard, D.J., Barrett, W.A.: Separating Lines of Text in Free-Form Handwritten Historical Documents. In: Int. Conf. on Document Image Analysis for Libraries, pp. 12–23, France (2006)Google Scholar
  7. 7.
    Leedham, G., et al.: Separating Text and Background in Degraded Document Images - A Comparison of Global Thresholding Techniques for Multi-Stage Thresholding. In: International Workshop on Frontiers in Handwriting Recognition, pp. 244–249, Canada (2002)Google Scholar
  8. 8.
    Mello, C.A.B., et al.: Image Thresholding of Historical Documents: Application to the Joaquim Nabuco’s File. In: Digital Cultural Heritage Conference - Eva Vienna, pp. 115–122, Vienna, Austria (2006)Google Scholar
  9. 9.
    Mello, C.A.B.: Image Segmentation of Historical Documents: Using a Quality Index. In: International Conference on Image Analysis and Recognition, pp. 209–216, Portugal (2004)Google Scholar
  10. 10.
    Mello, C.A.B., et al.: Image Segmentation of Historical Documents. Visual (2000), Mexico (2000)Google Scholar
  11. 11.
    Parker, J.R.: Algorithms for Image Processing and Computer Vision. John Wiley & Sons, Chichester (1997)Google Scholar
  12. 12.
    Rodrigues, P.S., et al.: Using Tsallis Entropy into a Bayesian Network for CBIR. In: Int. Conf. on Image Processing, pp. 1028–1031, Genova (2005)Google Scholar
  13. 13.
    Sezgin, M., et al.: Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging, vol. 13(1) (2004)Google Scholar
  14. 14.
    Shannon, C.: A Mathematical Theory of Communication. Bell System Technology Journal 27, 370–423 (1948)MathSciNetGoogle Scholar
  15. 15.
    Shi, Z., Govindaraju, V.: Historical Document Image Enhancement Using Background Light Intensity Normalization. In: International Conference on Pattern Recognition, pp. 473–476, UK (2004)Google Scholar
  16. 16.
    Tan, C.L., et al.: Removal of Interfering Strokes in Double-Sided Document Images. In: Workshop on Applications of Computer Vision, pp. 16–21, USA (2000)Google Scholar
  17. 17.
    Tan, C.L., et al.: Restoration of Archival Documents Using a Wavelet Technique. IEEE Trans.on Pattern Analysis and Machine Intelligence 24(10), 1399–1404 (2002)CrossRefGoogle Scholar
  18. 18.
    Tsallis, C.: Possible Generalization of Boltzmann-Gibbs statistics. Journal of Statistical Physics 52(1-2), 479–487 (1988)zbMATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Yan, L., et al.: An Application of Tsallis Entropy Minimum Difference on Image Segmentation, World Congress on Intelligent Control and Automation, pp. 9557–9561, China (2006)Google Scholar
  20. 20.
    Yan, L., et al.: Image Segmentation based on Tsallis-entropy and Renyi entropy and Their Comparison. In: Int. Conf. on Industrial Informatics, pp. 943–948, Singapore (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Carlos A. B. Mello
    • 1
  1. 1.Department of Computing Systems, University of Pernambuco, Recife, 50720-001Brazil

Personalised recommendations