Advertisement

A Holistic Classification System for Check Amounts Based on Neural Networks with Rejection

  • M. J. Castro
  • W. Díaz
  • F. J. Ferri
  • J. Ruiz-Pinales
  • R. Jaime-Rivas
  • F. Blat
  • S. España
  • P. Aibar
  • S. Grau
  • D. Griol
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3776)

Abstract

A holistic classification system for off-line recognition of legal amounts in checks is described in this paper. The binary images obtained from the cursive words are processed following the human visual system, employing a Hough transform method to extract perceptual features. Images are finally coded into a bidimensional feature map representation. Multilayer perpeptrons are used to classify these feature maps into one of the 32 classes belonging to the CENPARMI database. To select a final classification system, ROC graphs are used to fix the best threshold values of the classifiers to obtain the best tradeoff between accuracy and misclassification.

References

  1. 1.
    Madhvanath, S., Govindaraju, V.: The role of holistic paradigms in handwritten word recognition. IEEE Trans. on PAMI 23, 149–164 (2001)Google Scholar
  2. 2.
    Suen, C.Y., et al.: Computer recognition of unconstrained handwritten numerals. Special Issue of Proc. IEEE 7, 1162–1180 (1992)Google Scholar
  3. 3.
    Ruiz-Pinales, J., Lecolinet, E.: Cursive handwriting recognition using the Hough transform and a neural network. In: ICPR, pp. 231–234 (2002)Google Scholar
  4. 4.
    Bridle, J.S.: Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters. In: Advances in Neural Information Processing Systems, vol. 3. Morgan Kaufmann, San Francisco (1990)Google Scholar
  5. 5.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. John Wiley and Sons, New York (2001)zbMATHGoogle Scholar
  6. 6.
    Ferri, C., Hernández-Orallo, J.: Cautious classifiers. In: ROCAI, pp. 27–36 (2004)Google Scholar
  7. 7.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation, pp. 319–362. MIT Press, Cambridge (1986)Google Scholar
  8. 8.
    Fawcett, T.: ROC Graphs: Notes and Practical Considerations for Researchers. HP Technical Report HPL-2003-4, HP Labs (2003) (Revised March 2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • M. J. Castro
    • 1
  • W. Díaz
    • 2
  • F. J. Ferri
    • 2
  • J. Ruiz-Pinales
    • 3
  • R. Jaime-Rivas
    • 3
  • F. Blat
    • 1
  • S. España
    • 1
  • P. Aibar
    • 4
  • S. Grau
    • 1
  • D. Griol
    • 1
  1. 1.Dep. Sistemas Informáticos y ComputaciónUniv. Politécnica de ValenciaSpain
  2. 2.Dep. InformáticaUniv. de ValènciaBurjassot, ValenciaSpain
  3. 3.FIMEE – Univ. de GuanajuatoSalamanca, GuanajuatoMexico
  4. 4.Dep. Lenguajes y Sistemas InformáticosUniv. Jaume ICastellónSpain

Personalised recommendations