Skip to main content
SpringerLink
Log in

Artificial Neural Networks and Fuzzy Logic for Recognizing Alphabet Characters and Mathematical Symbols

  • Conference paper
  • First Online:
Computers Helping People with Special Needs (ICCHP 2016)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 9758))

Abstract

Optical Character Recognition software (OCR) are important tools for obtaining accessible texts. We propose the use of artificial neural networks (ANN) in order to develop pattern recognition algorithms capable of recognizing both normal texts and formulae. We present an original improvement of the backpropagation algorithm. Moreover, we describe a novel image segmentation algorithm that exploits fuzzy logic for separating touching characters.

R. Rossini—This work has been developed in the framework of an agreement between IRIFOR/UICI (Institute for Research, Education and Rehabilitation/Italian Union for the Blind and Partially Sighted) and Turin University.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Adam, S., Karras, D.A., Vrahatis, M.N.: Revisiting the problem of weight initialization for multi-layer perceptrons trained with back propagation. In: Köppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008, Part II. LNCS, vol. 5507, pp. 308–315. Springer, Heidelberg (2009)

    Chapter  Google Scholar 

  2. Adam, S.P., Karras, D.A., Magoulas, G.D., Vrahatis, M.N.: Solving the linear interval tolerance problem for weight initialization of neural networks. Neural Netw. 54, 17–37 (2014)

    Article  MATH  Google Scholar 

  3. Bishop, C.M.: Neural Networks for Pattern Recognition. Clarendon Express, Oxford (1995)

    MATH  Google Scholar 

  4. Cireşan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Deep big multilayer perceptrons for digit recognition. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, 2nd edn, pp. 581–598. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  5. Erdogmus, D., Romero, O.F., Principe, J.C.: Linear-least-squares initialization of multilayer perceptrons through backpropagation of the desired response. IEEE Trans. Neural Netw. 16(2), 325–336 (2005)

    Article  Google Scholar 

  6. Hajiyev, C., Caliskan, F.: Fault Diagnosis and Reconfiguration in Flight Control Systems. Springer, Heidelberg (2003)

    Book  MATH  Google Scholar 

  7. Garain, U., Chaudhuri, B.B.: Segmentation of touching symbols for OCR of printed mathematical expressions: an approach based on multifactorial analysis. In: 8th International Conference in Documents Analysis and Recognition, pp. 177–181 (2005)

    Google Scholar 

  8. Gray, R.M.: Toeplitz and circulant matrices: a review. Found. Trends Commun. Inf. Theor. 2(3), 155–239 (2006)

    Article  MATH  Google Scholar 

  9. Hsiao, T.C., Lin, C.W., Chiang, H.K.: Partial least squares algorithm for weight initialization of backpropagation network. Neurocomputing 5, 237–247 (2003)

    Article  MATH  Google Scholar 

  10. Kumar, A., Yadav, M., Patnaik, T., Kumar, B.: A survey on touching charcter segmentation. Int. J. Eng. Adv. Technol. 2(3), 569–574 (2013)

    Google Scholar 

  11. Lecun, Y., Cortes, C., Burges, C.J.C.: The MNIST database of handwriteen digits. http://yann.lecun.com/exdb/mnist

  12. Liang, S., Shridhar, M., Ahmadi, M.: Segmentation of touching characters in printed document recognition. Pattern Recogn. 27(6), 825–840 (1994)

    Article  Google Scholar 

  13. Lu, Y.: Machine printed character segmentation - an overview. Pattern Recogn. 28(1), 67–80 (1995)

    Article  Google Scholar 

  14. Murru, N., Rossini, R.: A Bayesian approach for initialization of weights in backpropagation neural net with application to character recognition. Neurocomputing (2016, to appear)

    Google Scholar 

  15. Saba, T., Sulong, G., Rahim, S., Rehman, A.: On the segmentation of multiple touched cursive characters: a heuristic approach. In: Das, V.V., Vijaykumar, R. (eds.) ICT 2010. CCIS, vol. 101, pp. 540–542. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  16. Sahlol, A.T., Suen, C.Y., Elbasyouni, M.R., Sallam, A.A.: A proposed OCR algorithm for the recognition of handwritten Arabic characters. J. Pattern Recogn. Intell. Syst. 2(1), 8–22 (2014)

    Google Scholar 

  17. Schrusolph, N.N.: Fast curvature matrix-vector products for second order gradient descent. Neural Comput. 14(7), 1723–1738 (2002)

    Article  MATH  Google Scholar 

  18. Shrivastava, V.: Artificial neural networks based optical character recognition. Sig. Image Process.: Int. J. 3(5), 73–80 (2012)

    MathSciNet  Google Scholar 

  19. Sodhi, S.S., Chandra, P.: Interval based weight initialization method for sigmoidal feedforward artificial neural networks. AASRI Procedia 6, 19–25 (2014)

    Article  Google Scholar 

  20. Suzuki, M., Kanahori, T., Ohtake, N., Yamaguchi, K.: An integrated OCR software for mathematical documents and its output with accessibility. In: Miesenberger, K., Klaus, J., Zagler, W.L., Burger, D. (eds.) ICCHP 2004. LNCS, vol. 3118, pp. 648–655. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Control and Computer Engineering, Politecnico di Torino, Corso Duca Degli Abruzzi 24, Torino, 10129, Italy

    Giuseppe Airò Farulla

  2. Department of Mathematics, University of Turin, Via Carlo Alberto 10, Torino, 10121, Italy

    Tiziana Armano, Anna Capietto & Nadir Murru

  3. Center for Applied Research on ICT, Istituto Superiore Mario Boella, Via Pier Carlo Boggio 61, Torino, 10138, Italy

    Rosaria Rossini

Authors
  1. Giuseppe Airò Farulla
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tiziana Armano
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Anna Capietto
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nadir Murru
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Rosaria Rossini
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nadir Murru .

Editor information

Editors and Affiliations

  1. Institute Integriert Studieren, Universität Linz, Linz, Austria

    Klaus Miesenberger

  2. Rehabilitationswissenschaften, Technische Universität Dortmund, Dortmund, Germany

    Christian Bühler

  3. Masaryk University , Brno, Czech Republic

    Petr Penaz

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Farulla, G.A., Armano, T., Capietto, A., Murru, N., Rossini, R. (2016). Artificial Neural Networks and Fuzzy Logic for Recognizing Alphabet Characters and Mathematical Symbols. In: Miesenberger, K., Bühler, C., Penaz, P. (eds) Computers Helping People with Special Needs. ICCHP 2016. Lecture Notes in Computer Science(), vol 9758. Springer, Cham. https://doi.org/10.1007/978-3-319-41264-1_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-41264-1_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-41263-4

  • Online ISBN: 978-3-319-41264-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation