Advertisement

Recent Approaches in Handwriting Recognition with Markovian Modelling and Recurrent Neural Networks

Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 26)

Abstract

Handwriting recognition is challenging because of the inherent variability of character shapes. Popular approaches for handwriting recognition are markovian and neuronal. Both approaches can take as input, sequences of frames obtained by sliding a window along a word or a text-line. We present markovian (Dynamic Bayesian Networks, Hidden Markov Models) and recurrent neural network-based approaches (RNNs) dedicated to character, word and text-line recognition. These approaches are applied to the recognition of both Latin and Arabic scripts.

Keywords

Word recognition Text-line recognition Hidden Markov Models Recurrent Neural Networks BLSTMs 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Vinciarelli, A.: Online and offline handwriting recognition: A comprehensive survey. Pattern Recognition 35(7), 1433–1446 (2002)CrossRefMATHGoogle Scholar
  2. 2.
    Plamondon, R., Srihari, S.: Online and offline handwriting recognition: A comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(1), 63–84 (2000)CrossRefGoogle Scholar
  3. 3.
    Graves, A., Liwicki, M., Fernandez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(5) (2009)Google Scholar
  4. 4.
    Likforman-Sulem, L., Sigelle, M.: Recognition of degraded characters using dynamic bayesian networks. Pattern Recognition 41(10), 3092–3103 (2008)CrossRefMATHGoogle Scholar
  5. 5.
    Murphy, K.: BayesNet Toolbox for Matlab (2003), http://www.ai.mit.edu/~murphyk/Bayes/bnintro.html
  6. 6.
    Likforman-Sulem, L., Sigelle, M.: ENST ancient character database (2008), http://perso.telecom-paristech.fr/~lauli/ENST_ANCIENT_CHAR/
  7. 7.
    Al-Hajj-Mohamad, R., Likforman-Sulem, L., Mokbel, C.: Combining slanted-frame classifiers for improved HMM-based arabic handwriting recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(7), 1165–1177 (2009)CrossRefGoogle Scholar
  8. 8.
    Bianne-Bernard, A.L., Menasri, F., El-Hajj, R., Mokbel, C., Kermorvant, C., Likforman-Sulem, L.: Dynamic and contextual information in HMM modeling for handwritten word recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(10) (2011)Google Scholar
  9. 9.
    Morillot, O., Likforman-Sulem, L., Grosicki, E.: New baseline correction algorithm for text-line recognition with bi-directional recurrent neural networks (2013)Google Scholar
  10. 10.
    Morillot, O., Likforman-Sulem, L., Grosicki, E.: Construction of language models for an handwritten mail reading system. In: Proceedings of Electronic Imaging - Document Recognition and Retrieval (DRR) XIX (2012)Google Scholar
  11. 11.
    Pechwitz, M., Maddouri, S.S., Märgner, V., Ellouze, N., Amiri, H.: IFN/ENIT- database of handwritten arabic words. In: Colloque International Francophone sur l’Ecrit et le Document (2002)Google Scholar
  12. 12.
    Märgner, V., El-Abed, H.: ICDAR 2009 Arabic Handwriting Recognition Competition. In: International Conference on Document Analysis and Recognition (2009)Google Scholar
  13. 13.
    Grosicki, E., El-Abed, H.: ICDAR 2009 handwriting recognition competition. In: International Conference on Document Analysis and Recognition, pp. 1398–1402 (2009)Google Scholar
  14. 14.
    Grosicki, E., El-Abed, H.: ICDAR 2011: French handwriting recognition competition. In: International Conference on Document Analysis and Recognition (2011)Google Scholar
  15. 15.
    NIST: OpenHart 2013 Evaluation (2013), http://www.nist.gov/itl/iad/mig/hart2013.cfm
  16. 16.
    Breuel, T.: OCRopus - Open Source Document Analysis and OCR system (2013), https://code.google.com/p/ocropus
  17. 17.
    Graves, A.: RNNlib (2009), http://www6.in.tum.de/Main/Graves
  18. 18.
    Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: Neural Information Processing Systems, pp. 545–552 (2008)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Institut Mines-TelecomTéléecom ParisTech & CNRS LTCIParisFrance

Personalised recommendations