Multi-component Document Image Coding Using Regions-of-Interest

  • Xiao Wei Yin
  • Andy C. Downton
  • Martin Fleury
  • J. He
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3163)


Region-of-Interest (ROI) techniques are often utilized in natural still-image coding standards such as JPEG2000 [1]. In contrast, document image coding typically adopts multi-layer methods [2], using a carefully selected algorithm for each layer to optimize overall performance. In this paper, an ROI-based method is proposed for multi-component document image coding, where rectangular textual ROI’s are easily extracted using standard document image analysis techniques. Compared to multi-layer methods, the method is simpler and scalable, while preserving comparable visual quality at equivalent PSNR.


Document Image Text Region Mask Layer Background Layer Document Analysis System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Christopoulos, C., Skodras, A., Ebrahimi, T.: The JPEG 2000 still image coding system: An overview. IEEE Transactions On Consumer Electronics 46, 1103–1127 (2000)CrossRefGoogle Scholar
  2. 2.
    Bottou, L., Haffner, P., Howard, P.G., Simard, P., Bengio, Y., Le Cun, Y.: High quality document image compression with DjVu. Journal of Electronic Imageing 7, 410–425 (1998)CrossRefGoogle Scholar
  3. 3.
    Howard, P.G.: Text image compression using soft pattern matching. The Computer Journal 40, 146–156 (1997)CrossRefGoogle Scholar
  4. 4.
    Haffner, P., Bottou, P., Howard, P.G., Simard, P., Bengio, Y., Le Cun, Y.: Browsing through high quality document images with DjVu. In: Advances in Digital Libaries, pp. 309–318 (1998)Google Scholar
  5. 5.
    Yin, X.W., Fleury, M., Downton, A.C.: Archive image communication with improved compression. In: ICDAR 2003, vol. 1, pp. 92–96 (2003)Google Scholar
  6. 6.
    Beccaloni, G., Scoble, M., Robinson, G., Pitkin, B.: The global lepidoptera names index (2002), at
  7. 7.
    Wong, K.Y., Casey, R.G., Wahl, F.M.: Document analysis system. IBM Journal of Research and Development 26, 647–656 (1982)CrossRefGoogle Scholar
  8. 8.
    Ha, J., Haralick, M., Phillips, R., Recursive, I.T.: X-Y cut using bounding boxes of connected components. In: ICDAR 1995, vol. II, pp. 952–955 (1995)Google Scholar
  9. 9.
    He, J., Downton, A.C.: Configurable text stamp identification tool with application of fuzzy logic. In: Marinai, S., Dengel, A.R. (eds.) DAS 2004. LNCS, vol. 3163, pp. 201–212. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    Christopoulos, C., Askelof, J., Larsson, M.: Efficient methods for encoding region of interest in the upcoming JPEG2000 still image coding standard. IEEE Signal Processing Letters 7, 247–249 (2000)CrossRefGoogle Scholar
  11. 11.
    Park, K., Park, H.W.: Region-of-interest coding based on set partitioning in hierarchical trees. IEEE Transactions On Circuits and Systems for Video Technology 12, 106–113 (2002)CrossRefGoogle Scholar
  12. 12.
    Said, A., Pearlman, W.A.: A new, fast, and efficient image codec based on set partitioning in hierarchical trees. IEEE Trans. on Circuits and Systems for Video Tech. 6, 243–250 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Xiao Wei Yin
    • 1
  • Andy C. Downton
    • 1
  • Martin Fleury
    • 1
  • J. He
    • 1
  1. 1.Department of Electronic Systems EngineeringUniversity of EssexUK

Personalised recommendations