The AddressScript™ Recognition System for Handwritten Envelopes

  • Alexander Filatov
  • Vadim Nikitin
  • Alexander Volgunin
  • Pavel Zelinsky
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1655)


This paper presents AddressScript-a system for handwritten postal address recognition for US mail. Key aspects of AddressScript technology, such as system control flow, cursive handwriting recognition, and postal database are described. Special attention is paid to the powerful character recognizer and the intensive usage of context, which becomes available during the recognition process. The algorithm of confidence level calculation is presented. Laboratory test results on a blind test set of 50,000 images of live hand-written mail pieces demonstrate a 64% finalization rate for error rates below USPS restrictions.


Street Address Address Block System Control Flow Handwritten Numeral Street Number 
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.
    Srihari, S.N. and Kuebert, E.J.: Integration of Hand-Written Address Interpretation Technology into the United States Postal Service Remote Computer Reader System. Proc. of the 4th Int. Conf. on Document Analysis and Recognition. Ulm, Germany. (1997) 892–896Google Scholar
  2. 2.
    Dzuba, G., Filatov, A., Gershuny, D., and Kil, I.: Handwritten Word Recognition–The Approach Proved by Practice. Proc. of the 6th Int. Workshop on Frontiers in Handwriting Recognition. Taejon, Korea. (1998) 99–111Google Scholar
  3. 3.
    Filatov, A., Gitis, A., and Kil, I.: Graph-Based Handwritten Digit String Recognition. Proc. of 3rd Int. Conf. on Document Analysis and Recognition. Montreal, Canada. (1995) 845–848Google Scholar
  4. 4.
    Fenrich, R. and Hull, J.J.: Concerns in Creation of Image Database. Proc. of the 3rd Int. Workshop on Frontiers in Handwriting Recognition. Buffalo, New York, USA, May 25-27, (1993) 112–121Google Scholar
  5. 5.
    Ha, T.M. and Bunke, H.: Handwritten Numeral Recognition by Perturbation Method. Proc. of the 4th Int. Workshop on Frontiers in Handwriting Recognition. Taipei, Taiwan, Republic of China. Dec. 7-9 (1994) 97–106Google Scholar
  6. 6.
    Lee, D.S. and Srihari, S.N.: Handprinted Digit Recognition: A Comparison of Algorithms. Proc. of the third Int. Workshop on Frontiers in Handwritting Recognition. Buffalo, New York, USA. May 25-27 (1993) 153–162Google Scholar
  7. 7.
    Knerr, S. and Sperduti, S.: Rejection Driven Hierarchy of Neural Network Classifiers. Proc. of 1993 Int. Symp. on Nonlinear Theory and its Applications. Vol. 3. Hawaii. (1993)Google Scholar
  8. 8.
    Dzuba, G., Filatov, A., and Volgunin, A.: Handwritten ZIP Code Recognition. Proc. of the 4th Int. Conf. on Document Analysis and Recognition. Ulm, Germany (1997) 766–770Google Scholar
  9. 9.
    Dzuba, G., Filatov, A., Gershuny, D., Kil, I., and Nikitin, V.: Check Amount Recognition based on the Cross Validation of Courtesy and Legal Amount Fields. In: Impedovo, S., Wang, P.S.P., Bunke, H. (eds.): Automatic Bankcheck Processing. World Scientific. (1997) 177–193Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Alexander Filatov
    • 1
  • Vadim Nikitin
    • 1
  • Alexander Volgunin
    • 1
  • Pavel Zelinsky
    • 1
  1. 1.ParaScript, LLCNiwotUSA

Personalised recommendations