Interactive, Mobile, Distributed Pattern Recognition

  • George Nagy
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3617)


As the accuracy of conventional classifiers, based only on a static partitioning of feature space, appears to be approaching a limit, it may be useful to consider alternative approaches. Interactive classification is often more accurate then algorithmic classification, and requires less time than the unaided human. It is more suitable for the recognition of natural patterns in a narrow domain like trees, weeds or faces than for symbolic patterns like letters and phonemes. On the other hand, symbolic patterns lend themselves better to using context and style to recognize entire fields instead of individual patterns. Algorithmic learning and adaptation is facilitated by accurate statistics gleaned from large samples in the case of symbolic patterns, and by skilled human judgment in the case of natural patterns. Recent technological advances like pocket computers, camera phones and wireless networks will have greater influence on mobile, distributed, interactive recognition of natural patterns than on conventional high-volume applications like mail sorting , check reading or forms processing.


Face Recognition Visible Model Natural Pattern Unknown Object Reference Picture 
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.
    Nagy, G.: Teaching a computer to read. In: Procs. Int’l Conf. Pattern Recognition (ICPR XI), The Hague, August 1992, vol. 2, pp. 225–229 (1992)Google Scholar
  2. 2.
    Sarkar, P., Nagy, G.: Style consistent classification of isogenous patterns. IEEE Trans. PAMI 27(1), 88–98 (2005)Google Scholar
  3. 3.
    Veeramachaneni, S., Nagy, G.: Style context with second order statistics. IEEE Trans. PAMI 27(1), 14–22 (2005)Google Scholar
  4. 4.
    Nagy, N., Zhang, X., Nagy, G., Schneider, E.W.: A quantitative categorization of phonemic dialect features in context. In: Procs. International Conference on Context, Paris (July 2005)Google Scholar
  5. 5.
    Nagy, G., Sarkar, P.: Document style census for OCR. In: Procs. First International Workshop on Document Image Analysis for Libraries (DIAL 2004), Palo Alto, CA, pp. 134–147. IEEE Computer Society Press, Los Alamitos (2004)CrossRefGoogle Scholar
  6. 6.
    Nagy, G., Veeramachaneni, S.: A Ptolemaic model for OCR. In: Procs. ICDAR 2003, Edinburgh, August 2003, pp. 1060–1064 (2003)Google Scholar
  7. 7.
    Nagy, G.: Visual pattern recognition in the years ahead. In: Procs. ICPR XVII, Cambridge, UK, August 2004, vol. IV, pp. 7–10 (2004)Google Scholar
  8. 8.
    Nagy, G., Zhang, X.: Simple statistics for complex features spaces. In: Basu, M., Ho, T.K. (eds.) Data Complexity in Pattern Recognition. Springer, Heidelberg (2005) (to appear)Google Scholar
  9. 9.
    Nagy, G., Zou, J.: Interactive visual pattern recognition. In: Procs. ICPR XVI, vol. III, pp. 478–481. IEEE Computer Society Press, Los Alamitos (2002)Google Scholar
  10. 10.
    Zou, J., Nagy, G.: Evaluation of model-based interactive pattern recognition. In: Procs. ICPR XVII, Cambridge, UK, August 2004, vol. II, pp. 311–314 (2004)Google Scholar
  11. 11.
    Zou, J., Nagy, G.: Human-computer interaction for complex pattern recognition problems. In: Basu, M., Ho, T.K. (eds.) Data Complexity in Pattern Recognition. Springer, Heidelberg (2005) (to appear)Google Scholar
  12. 12.
    Evans, A., Sikorski, J., Thomas, P., Cha, S.-H., Tappert, C., Zou, J., Gattani, A., Nagy, G.: Computer Assisted Visual Interactive Recognition (CAVIAR) Technology. In: Procs. IEEE International Conference on Electro-Information Technology, Lincoln, NE (May 2005)Google Scholar
  13. 13.
    Zou, J.: A Model-Based Interactive Image Segmentation Procedure. In: IEEE Workshop on Applications of Computer Vision (WACV), Breckenridge CO (January 2005)Google Scholar
  14. 14.
    Nagy, G., Shelton, G.L.: Self-Corrective Character Recognition System. IEEE Transactions on Information Theory IT-12(2), 215–222 (1966)CrossRefGoogle Scholar
  15. 15.
    Baird, H.S., Nagy, G.: A Self-correcting 100-font Classifier. In: Proc. SPIE Conference on Document Recognition, San Jose, CA, February 1994, vol. SPIE-2181, pp. 106–115 (1994)Google Scholar
  16. 16.
    Veeramachaneni, S., Nagy, G.: Adaptive classifiers for multi-source OCR. IJDAR 6(3), 154–166 (2004)CrossRefGoogle Scholar
  17. 17.
    Nagy, G.: Classifiers that improve with use. In: Procs. Conference on Pattern Recognition and Multimedia, IEICE, Tokyo, February 2004, pp. 79–86 (2004)Google Scholar
  18. 18.
    Gattani, A.: Mobile Interactive Visual Pattern Recognition. MS thesis, Rensselaer Polytechnic Institute (December 2004)Google Scholar
  19. 19.
    Raghunath, M., Narayanaswami, C., Pinhanez, C.: Fostering a Symbiotic Handheld Environment. IEEE Computer, 56–65 (September 2004)Google Scholar
  20. 20.
    Zou, J., Gattani, A.: Computer Assisted Visual InterActive Recognition and Its Prospects of Implementation Over the Internet. In: IS&T/SPIE 17th Annual Symposium Electronic Imaging, Internet Imaging VI (2005)Google Scholar
  21. 21.
    Casey, R.G., Nagy, G.: Autonomous Reading Machine. IEEE Transactions on Computers C-17(5), 492–503 (1968)CrossRefGoogle Scholar
  22. 22.
    Casey, R.G., Nagy, G.: Advances in Pattern Recognition. Scientific American 224(4), 56–71 (1971)CrossRefGoogle Scholar
  23. 23.
    Nagy, G., Seth, S., Einspahr, K.: Decoding Substitution Ciphers by means of Word Matching with Application to OCR. IEEE Transactions on Pattern Analysis and Machine Intelligence 9(5), 710–715 (1987)CrossRefGoogle Scholar
  24. 24.
    Ho, T.K., Nagy, G.: OCR with no shape training. In: Procs. ICPR-XV, Barcelona, September 2000, vol. 4, pp. 27–30 (2000)Google Scholar
  25. 25.
    Veeramachaneni, S., Sarkar, P., Nagy, G.: Modeling context as statistical dependence. In: Procs. International Conference on Context, Paris (July 2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • George Nagy
    • 1
  1. 1.DocLabRensselaer Polytechnic InstituteTroyUSA

Personalised recommendations