Improving Still Image Coding by an SOM-Controlled Associative Memory

  • Gerald Krell
  • René Rebmann
  • Udo Seiffert
  • Bernd Michaelis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2905)


Archiving of image data often requires a suitable data reduction to minimise the memory requirements. However, these compression procedures entail compression artefacts, which make machine processing of the captured documents more difficult and reduce subjective image quality for the human viewer. A method is presented which can reduce the occurring compression artefacts. The corrected image yields as output of an auto-associative memory that is controlled by a Self-Organising Map (SOM).


Image Compression Associative Memory Image Block Image Class JPEG Compression 
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.
    Abbas, H.M., Fahmy, M.M.: A Neural Model for Adaptive Karhunen Loéve Transformation (KLT). In: Proc. International Joint Conference on Neural Networks, Baltimore, Maryland, vol. 2, pp. 975–980 (1992)Google Scholar
  2. 2.
    ISO/IEC JTC1 10918-1, ITU-T Rec. T.81, Information technology - Digital compression and coding of continuous-tone still images: Requirements and guidelines (1994)Google Scholar
  3. 3.
    ISO/IEC JTC 1/SC 29/WG 1: Coding of Still Pictures - JPEG 2000. Part 1 Final Committee Draft Version 1.0 (2000)Google Scholar
  4. 4.
    Kielbasinski, A., Schwetlick, H.: Numerische Lineare Algebra. Deutscher Verlag der Wissenschaften, Berlin (1988)zbMATHGoogle Scholar
  5. 5.
    Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer, London (2001)zbMATHGoogle Scholar
  6. 6.
    Lilienblum, T., Albrecht, P., Calow, R., Michaelis, B.: Dent Detection in Car Bodies. In: 15th International Conference on Pattern Recognition (ICPR), Barcelona, September 3-8, vol. 4, pp. 775–778 (2000)Google Scholar
  7. 7.
    Obermayer, K., Sejnowski, T.J. (eds.): Self-Organizing Map Formation – Foundations of Neural Computation. The MIT Press, Cambridge (2001)Google Scholar
  8. 8.
    Rebmann, R., Krell, G., Michaelis, B.: Reduction of Compression Artefacts Caused by JPEG Compression. In: Proceedings of the VIIP2002, September 9-12, pp. 271–275. ACTA Press, Malaga (2002)Google Scholar
  9. 9.
    Amerijckx, C., Thissen, P.: Image Compression by Self-Organized Kohonen Map. IEEE Transactions on Neural Networks 9(3), 503–507 (1998)CrossRefGoogle Scholar
  10. 10.
    Seiffert, U., Jain, L.C. (eds.): Self-Organizing Neural Networks – Recent Advances and Applications. Springer, Heidelberg (2001)zbMATHGoogle Scholar
  11. 11.
    Tizhoosh, H.R., Michaelis, B.: Image Enhancement Based on Fuzzy Aggregation techniques. In: IMTC 1999, Proceedings of the 16th IEEE converence, pp. 1813–1817 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Gerald Krell
    • 1
  • René Rebmann
    • 1
  • Udo Seiffert
    • 2
  • Bernd Michaelis
    • 1
  1. 1.Otto-von-Guericke UniversityMagdeburgGermany
  2. 2.Leibniz Institute of Plant Genetics and Crop Plant Research GaterslebenGermany

Personalised recommendations