Handwritten Numerical Character Recognition Based on Paraconsistent Artificial Neural Networks

Part of the Studies in Computational Intelligence book series (SCI, volume 513)

Abstract

This paper presents an automated computational process able to recognize a handwritten numerical characters and Magnetic Ink Character Recognition used on bank checks based on Paraconsistent Artificial Neural Networks. The methodology employed was chosen for being a tool able to work with imprecise, inconsistent and paracomplete data without trivialization. The recognition process is performed from some character features previously selected based on some Graphology and Graphoscopy techniques and, the analysis of such features as well as the character recognition are performed by Paraconsistent Artificial Neural Networks.

Keywords

Artificial Intelligence Pattern Recognition Character Recognition Handwritten Numerical Character Recognition Artificial Neural Networks Paraconsistent Artificial Neural Networks 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abe, J.M.: Foundations of Annotated Logics. PhD thesis, University of São Paulo, Brazil (1992) (in Portuguese)Google Scholar
  2. 2.
    Abe, J.M.: Some Aspects of Paraconsistent Systems and Applications. Logique et Analyse 157, 83–96 (1997)Google Scholar
  3. 3.
    Abe, J.M., Lopes, H.F.S., Anghinah, R.: Paraconsistent Artificial Neural Network and Alzheimer Disease: A Preliminary Study. Dementia & Neuropsychologia 3, 241–247 (2007)Google Scholar
  4. 4.
    Abdleazeem, S., El-Sherif, E.: Arabic handwritten digit recognition. International Journal of Document Analysis and Recognition (IJDAR) 11(3), 127–141 (2008)CrossRefGoogle Scholar
  5. 5.
    Amend, K., Ruiz, M.S.: Handwriting Analysis: The Complete Basic Book. Franklin Lakes, NJ (1980)Google Scholar
  6. 6.
    Bortolozzi, F., Brittto Jr., A.S., Oliveira, L.E.S., Morita, M.: Recent Advances in Handwriting Recognition. In: Pal, U., Parui, S.K., Chaudhuri, B.B. (Org.) Document Analysis, Chennai, pp. 1–30 (2005)Google Scholar
  7. 7.
    Da Silva Filho, J.I.: Paraconsistent algorithm extractor of contradiction’s effects - ParaExtrctr. Seleção Documental 15, 21–25 (2009) (in Portuguese)Google Scholar
  8. 8.
    Da Silva Filho, J.I., Torres, G.L., Abe, J.M.: Uncertainty Treatment Using Paraconsistent Logic – Introducing Paraconsistent Artificial Neural Networks. IOS Press, Netherlands (2010)MATHGoogle Scholar
  9. 9.
    Fujisawa, Y., Shi, M., Wakabayashi, T., Kimura, F.: Handwritten Numeral Recognition Using Gradient and Curvature of Gray Scale Image. In: Proceedings of the Fifth International Conference on ICDAR 1999, Bangalore, pp. 277–280 (1999)Google Scholar
  10. 10.
    Haykin, S.: Neural Networks. McMaster University, Toronto (1994)MATHGoogle Scholar
  11. 11.
    Lopes, H.F.S., Abe, J.M., Anghinah, R.: Application of Paraconsistent Artificial Neural Networks as a Method of Aid in the Diagnosis of Alzheimer Disease. Journal of Medical Systems 34(6), 1073–1081 (2010)CrossRefGoogle Scholar
  12. 12.
    Lopes, H.F.S., Abe, J.M., Kanda, P.A.M., Machado, S., Velasques, B., Ribeiro, P., Basile, L.F.H., Nitrini, R., Anghinah, R.: Improved Application of Paraconsistent Artificial Neural Networks in Diagnosis of Alzheimer’s Disease. American Journal of Neuroscience 2(1), 54–64 (2011)CrossRefGoogle Scholar
  13. 13.
    Mario, M.C., Abe, J.M., Ortega, N., Del Santo Jr., M.: Paraconsistent Artificial Neural Network as Auxiliary in Cephalometric Diagnosis. Artificial Organs. 34(7), 215–221 (2010)CrossRefGoogle Scholar
  14. 14.
    Mori, S., Suen, C.Y., Yamamoto, K.: Historical Review of OCR research and Development. Journals & Magazines 80(7), 1029–1058 (1992)Google Scholar
  15. 15.
    Trier, O.D., Jain, A.K., Taxt, T.: Feature extraction methods for character recognition - a survey. Pattern Recognit. 29(4), 641–662 (1996)CrossRefGoogle Scholar
  16. 16.
    Hammerstrom, D.: Adaptative Solutions Inc. Spectrum 30(6), 26–32 (1993)CrossRefGoogle Scholar
  17. 17.
    Öksüz, O.: Vision Based Handwritten Character Recognition. M.S. thesis. Bilkent University, Turkey (2003)Google Scholar
  18. 18.
    Javadevan, R., Kolhe, S.R., Patil, P.M., Pal, U.: Automatic processing of handwritten bank cheque images: a survey. IJDAR 15(4), 267–296 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.School of MedicineUniversity of São PauloSão PauloBrazil
  2. 2.Institute for Advanced StudiesUniversity of São PauloSão PauloBrazil
  3. 3.PRODESPData Processing Company of São Paulo StateSão PauloBrazil
  4. 4.Graduate Program in Production Engineering, ICETPaulista UniversitySão PauloBrazil

Personalised recommendations