Multilevel Recognition of Structured Handprinted Documents - Probabilistic Approach

  • Jerzy Sas
  • Marek Kurzynski
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 30)


In the paper the multilevel probabilistic approach to handprinted form recognition is described. The form recognition is decomposed into three levels: character recognition, word recognition and form contents recognition. On the word and form contents level the probabilistic lexicons are available. The decision on the word level is performed using probabilistic properties of character classifier and the contents of probabilistic lexicon. The novel approach to combining these two sources of information about classes (words) probabilities is proposed, which is based on lexicons and accuracy assessment of local character classifiers. Some experimental results and examples of practical applications of recognition method are also briefly described.


Word Recognition Recognition Quality Character Classifier Word Level Word Classifier 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kuncheva L.I. (2002) A Theoretical Study on Six Classifier Fusion Strategies, IEEE Trans. on Pattern Anal. and Machine Intelligence, Vol. 24, No 2: 281–286CrossRefGoogle Scholar
  2. 2.
    Chen W.T., Gader P., Shi H. (1999) Lexicon-Driven Handwritten Word Recognition Using Optimal Linear Combination of Order Statistics, IEEE Trans. on Pattern Anal. and Machine Intelligence, Vol 21, No 1: 71–82Google Scholar
  3. 3.
    Grandidier F., Sabourin R. (2000) A New Strategy for Improving Features Set in a Discrete HMM-based Handwriting Recognition System, In: Schomaker L.R.B., Vuurpijl (eds) Proceedings of the Seventh International Workshop on Frontiers in Handwritting Recognition, Sept. 11–13 2000 Amsterdam: 113–122Google Scholar
  4. 4.
    Kim J. H., Kim K.K., Suen C. Y. (2000) An HMM-MLP Hybrid Model for Cursive Script Recognition. Pattern Analysis and Applications, No 3: 312–324MathSciNetCrossRefGoogle Scholar
  5. 5.
    Kuncheva L.I. (2001) Using Measures of Similarity and Inclusion for Multiple Classifier Fusion by Decision Templates, Fuzzy Sets and Systems, 122(3): 401–407zbMATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Liu C., Nakashima K., Sako H., Fujisawa H. (2003) Handwritten Digit Recognition: Benchmarking of State-of-the-Art Techniques, Pattern Recognition, Vol. 36: 2271–2285zbMATHCrossRefGoogle Scholar
  7. 7.
    Lu Y., Gader P., Tan C. L. (2002) Combination of Multiple Classifiers Using Probabilistic Dictionary and its Application to Postcode Generation, Pattern Recognition, Vol 35: 2823–2832zbMATHCrossRefGoogle Scholar
  8. 8.
    Sas J. (2004) Handwritten Laboratory Test Order Form Recognition Module For Distributed Clinic, Journ. of Medical Informatics & Technologies, Vol 8: 59–68Google Scholar
  9. 9.
    Sas J. (2004) Three-Level, Lexicon-Based Handwritten Form Recognition Method, In: Klopotek M., Tchorzewski J. (eds) Proc, of VI Int. Conf on Artificial Intelligence AI-19’2004, Vol. 1(23): 113–124Google Scholar
  10. 10.
    Vinciarelli A., Bengio S., Bunke H. (2004) Offline Recognition of Unconstrained Handwritten Texts Using HMMs and Statistical Language Models, IEEE Trans. on Pattern Anal. and Machine Intelligence, Vol 26, No 6: 709–720CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Jerzy Sas
    • 1
  • Marek Kurzynski
    • 2
  1. 1.Institute of Applied InformaticsWroclaw University of TechnologyWroclawPoland
  2. 2.Faculty of Electronics, Chair of Systems and Computer NetworksWroclaw University of TechnologyWroclawPoland

Personalised recommendations