Word Recognition by MLP-based Character Spotting and Dynamic Programming

  • F. Camastra
  • E. Cepollina
  • A. M. Colla
Conference paper
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)

Abstract

This paper describes a method for handprinted word recognition, with the following characteristics: traditional pre-processing (relevant to single characters, obtained by word segmentation) is replaced by pre-processing based on piecewise normalization applied at whole words; feature extraction and character classification by MLP are performed in a sliding window fashion; the output string is matched with an ASCII word vocabulary by Dynamic Programming with the Levenshtein distance; a list of word candidates is issued. Afterwards, when the language is formally known, an appropriate parser can be applied to full Sentence Recognition. Tests on a medium size vocabulary show extremely promising results.

Keywords

Diphone 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Matan CJ., Burges C., Le Cun Y. and Denker JS. Multi-digit recognition using a space displacement neural network. In: Advances in Neural Information Processing Systems, vol. 4, pp. 488–495, 1991Google Scholar
  2. [2]
    Martin G. and Rashid M. Recognizing overlapping hand-printed characters by centered-object integrated segmentation and recognition. In: Advances in Neural Information Processing Systems, vol. 4, pp. 504–511, 1991Google Scholar
  3. [3]
    Keeler J. and Rumelhart DE. A self-organizing integrated segmentation and recog¬nition neural net. In: Advances in Neural Information Processing Systems, vol. 4, pp. 496–503, 1991Google Scholar
  4. [4]
    Scagliola C., Carossino A., Colla AM. et al. Real-Time Large Vocabulary Word Recognition via Diphone Spotting and Multiprocessor Implementation. Speech Comm. 1988; 7: 389–396CrossRefGoogle Scholar
  5. [5]
    Hertz J., Krogh A. and Palmer RG. An Introduction to Neural Computation. Addison-Wesley, 1991Google Scholar
  6. [6]
    Colla AM. and Pedrazzi P. Single and Coupled Neural Handprinted Character Classifiers. In: M. Marinaro and P.G. Morasso (Eds), ICANN 94 - Proc. of the Int. Conf. on ARTIFICIAL NEURAL NETWORKS. Sorrento (Italy), vol. II, pp. 969–972, Springer-Verlag, 1994Google Scholar
  7. [7]
    Cepollina E. Metodi avanzati per il riconoscimento del manoscritto. Tesi di Laurea in Scienza dell’Inform azione (M. Sci. Thesis in Computer Science ). DISI Univ. di Genova, 1996Google Scholar
  8. [8]
    Pedrazzi P. and Colla AM. Simple Feature Extraction For Handwritten Character Recognition. In: Proc. IEEE 1995 Int. Conference on Image Processing ICIP-95. Washington, vol. Ill, pp. 320–323, 1995Google Scholar
  9. [9]
    Aho AV. and Ullman JD. Principles of Compiler Design. Addison-Wesley, Reading (USA ), 1978MATHGoogle Scholar
  10. [10]
    Sakoe H. and Chiba S. Dynamic Programming algorithm Optimization for Spo¬ken Word Recognition. IEEE Trans. ASSP-26, 1, pp. 43–49, 1978Google Scholar

Copyright information

© Springer-Verlag London Limited 1998

Authors and Affiliations

  • F. Camastra
    • 1
  • E. Cepollina
    • 2
  • A. M. Colla
    • 1
  1. 1.Elsag Bailey - Un’Azienda Finmeccanica S.p.AGenovaItaly
  2. 2.Dip. Informatica e Scienze dell’InformazioneUniversità di GenovaGenovaItaly

Personalised recommendations