A Biologically Plausible SOM Representation of the Orthographic Form of 50,000 French Words

  • Claude Touzet
  • Christopher Kermorvant
  • Hervé Glotin
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 295)

Abstract

Recently, an important aspect of human visual word recognition has been characterized. The letter position is encoded in our brain using an explicit representation of order based on letter pairs: the open-bigram coding [15]. We hypothesize that spelling has evolved in order to minimize reading errors. Therefore, word recognition using bigrams — instead of letters — should be more efficient. First, we study the influence of the size of the neighborhood, which defines the number of bigrams per word, on the performance of the matching between bigrams and word. Our tests are conducted against one of the best recognition solutions used today by the industry, which matches letters to words. Secondly, we build a cortical map representation of the words in the bigram space — which implies numerous experiments in order to achieve a satisfactory projection. Third, we develop an ultra-fast version of the self-organizing map in order to achieve learning in minutes instead of months.

Keywords

Handwriting recognition word recognition open-bigram coding orthographic representation cortical representation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Impedovo, S.: More than twenty years of advancements on Frontiers in Handwriting Recognition. Pattern Recognition (June 12, 2013) (in press)Google Scholar
  2. 2.
    Chen, W., Gader, P., Shi, H.: Lexicon-driven handwritten word recognition using optimal linear combinations of order statistics. IEEE Trans. Pattern Anal. Mach. Intell. 21(1), 77–82 (1999)CrossRefGoogle Scholar
  3. 3.
    Salome, J., Leroux, M., Badard, J.: Recognition of cursive script words in a small lexicon. In: Proc. of ICDAR 2011, pp. 774–782 (1991)Google Scholar
  4. 4.
    Cho, W., Lee, S., Kim, J.H.: Modeling and recognition of cursive words with hidden Markov models. Pattern Recognition 28(12), 1941–1953 (1995)CrossRefGoogle Scholar
  5. 5.
    Xue, H., Govindaraju, V.: Incorporating Contextual Character Geometry in Word Recognition. In: Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition, pp. 123–127 (2002)Google Scholar
  6. 6.
    Oh, I.-S., Suen, C.Y.: A class-modular feedforward neural network for handwriting recognition. Pattern Recognition 35(1), 229–244 (2002)MATHCrossRefGoogle Scholar
  7. 7.
    Senior, A.W., Fallside, F.: An off-line cursive script recognition system using recurrent error propagation networks. In: Proc. Third Intl. W. F. Hand-Writing Recog., pp. 132–141 (1993)Google Scholar
  8. 8.
    Laaksonen, J.: Subspace classifiers in recognition of handwritten digits, PhD thesis, Helsinki University of Technology (1997)Google Scholar
  9. 9.
    Graves, A., Schmidhuber, J.: Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks. In: Bengio, Y., Schuurmans, D., Lafferty, J., Williams, C.K.I., Culotta, A. (eds.) Advances in Neural Information Processing Systems 22 (NIPS 22), Vancouver, BC, pp. 545–552 (2009)Google Scholar
  10. 10.
    Graves, A., Liwicki, M., Fernandez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A Novel Connectionist System for Improved Unconstrained Handwriting Recognition. IEEE Trans. Pattern Analysis and Machine Intelligence 31(5), 855-868 (2009)Google Scholar
  11. 11.
    Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Convolutional Neural Network Committees For Handwritten Character Classification. In: Proc. of ICDAR 2011, Beijing, China, pp. 1135–1139 (2011)Google Scholar
  12. 12.
    Ciresan, D.C., Meier, U., Schmidhuber, J.: Multi-column Deep Neural Networks for Image Classification. In: IEEE CVPR, pp. 3642–3649 (2012)Google Scholar
  13. 13.
    LeCun, Y., Bottou, L., Bengio, Y., Haner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  14. 14.
    Dehaene, S., Cohen, L., Sigman, M., Vinckier, F.: The neural code for written words: A proposal. Trends in Cognitive Sciences 9, 335–341 (2005)CrossRefGoogle Scholar
  15. 15.
    Whitney, C., Bertrand, D., Grainger, J.: On coding the position of letters in words: A test of two models. Experimental Psychology 59(2), 109–114 (2012)CrossRefGoogle Scholar
  16. 16.
    RIMES: Reconnaissance et Indexation de données Manuscrites et de fac-similÉS / Recognition and Indexing of handwritten documents and faxes, http://www.rimes-database.fr
  17. 17.
    Menasri, F., Louradour, J., Bianne-Bernard, A.-L., Kermorvant, C.: The A2iA French handwriting recognition system at the Rimes-ICDAR2011 competition. In: Chien, L.-C., Lee, S.-D., Wu, M.H. (eds.) Document Recognition and Retrieval Conference, Proceedings of the SPIE, vol. 8297, p. 8 (2012)Google Scholar
  18. 18.
    Ortga, É., Lété, B.: eManulex: Electronic version of Manulex and Manulex-infra databases (2010), http://www.manulex.org
  19. 19.
    Dufau, S., Lété, B., Touzet, C., Glotin, H., Ziegler, J., Grainger, J.: Developmental Perspective on Visual Word Recognition: New Evidence and a Self-Organizing Model. European Journal of Cognitive Psychology 22(5), 669–694 (2010)CrossRefGoogle Scholar
  20. 20.
    Kohonen, T.: Self-organizing maps. 3rd Extended edn. Springer, Heidelberg (2001)Google Scholar
  21. 21.
    Touzet, C.: Why Neurons are Not the Right Level of Abstraction for Implementing Cognition. In: BICA 2012: Annual Int. Conf. on Biologically Inspired Cognitive Architectures, Palermo, Italy, pp. 317–318 (2012)Google Scholar
  22. 22.
    Touzet, C.: The Illusion of Internal Joy. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds.) AGI 2011. LNCS, vol. 6830, pp. 357–362. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  23. 23.
    Touzet, C.: Consciousness, Intelligence, Free-Will? The answers from the Theory of neuronal Cognition. La Machotte Ed., Auriol, France (2010) (in French)Google Scholar
  24. 24.
    Bluche, T., Louradour, J., Knibbe, M., Moysset, B., Benzeghiba, F., Kermorvant, C.: The A2iA Arabic Handwritten Text Recognition System at the OpenHaRT2013 Evaluation (submitted, 2014)Google Scholar
  25. 25.
    Kohonen, T., Somervuo, P.: Self-Organizing Maps of Symbol Strings with Application to Speech Recognition. In: Proc. of WSOM 1997, Espoo, FI, pp. 2–7 (1997)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Claude Touzet
    • 1
  • Christopher Kermorvant
    • 2
  • Hervé Glotin
    • 3
  1. 1.Aix-Marseille University (AMU), Lab. de Neurosciences Intégratives et AdaptativesLNIA UMR-CNRS 7260, Pôle Cerveau-Comportement-CognitionMarseilleFrance
  2. 2.A2iA SA (Analyse d’Image & Intelligence Artificielle)ParisFrance
  3. 3.Institut Univ. de France (IUF) & Univ. Aix-Marseille (AMU), Univ. Toulon (UTLN), ENSAM, Lab. des Sciences de l’Information et des Systèmes (LSIS)UMR CNRS 7296ToulonFrance

Personalised recommendations