Skip to main content
SpringerLink
Log in
Book cover

Workshop of Physical Agents

WAF 2018: Advances in Physical Agents pp 87–99Cite as

Convolutional Neural Network vs Traditional Methods for Offline Recognition of Handwritten Digits

  • Conference paper
  • First Online:

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 855))

Abstract

This paper compares Convolutional Neural Networks vs traditional features extraction and classification techniques for an offline recognition of handwritten digits application. The studied classification techniques are: k-NN, Mahalanobis distance and Support Vector Machines (SVM); and the hand-designed features extraction ones are: Hu Invariant Moments, Fourier Descriptors, Projections Histograms, Horizontal Cell Projections, Local Line Fitting and Zoning. The study was conducted in a practical application as is the validation of democratic elections using ballots of electoral scrutiny with non-homogeneous background. To do that it was necessary to use different preprocessing techniques (RGB conversion to gray scale, binarization and noise reduction) as well as a segmentation stage.

This is a preview of subscription content, 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   129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   169.99
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

Learn about institutional subscriptions

References

  1. Manoj, A., Borate, P., Jain, P., Sanas, V., Pashte, R.: A survey on offline handwriting recognition systems (2016)

    Google Scholar 

  2. Parizeau, M., Lemieux, A., Gagné, C.: Character recognition experiments using Unipen data. In: ICDAR, p. 0481. IEEE (2001)

    Google Scholar 

  3. Ghosh, R., Ghosh, M., et al.: An intelligent offline handwriting recognition system using evolutionary neural learning algorithm and rule based over segmented data points. J. Res. Pract. Inf. Technol. 37(1), 73 (2005)

    MathSciNet  Google Scholar 

  4. Nguyen, V., Blumenstein, M.: Techniques for static handwriting trajectory recovery: a survey. In: Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, pp. 463–470. ACM (2010)

    Google Scholar 

  5. LeCun, Y., Bengio, Y., et al.: Convolutional networks for images, speech, and time series. Handb. Brain Theory Neural Netw. 3361(10), 1995 (1995)

    Google Scholar 

  6. Bouchain, D.: Character recognition using convolutional neural networks. In: Institute for Neural Information Processing, vol. 2007 (2006)

    Google Scholar 

  7. Lauer, F., Suen, C.Y., Bloch, G.: A trainable feature extractor for handwritten digit recognition. Pattern Recogn. 40(6), 1816–1824 (2007)

    Article  Google Scholar 

  8. Gonzalez, R.C., Woods, R.E., Eddins, S.L., et al.: Digital Image Processing Using MATLAB, vol. 624. Pearson-Prentice-Hall, Upper Saddle River (2004)

    Google Scholar 

  9. Hu, M.-K.: Visual pattern recognition by moment invariants. IRE Trans. Inf. Theory 8(2), 179–187 (1962)

    Article  Google Scholar 

  10. Cuevas, E., Zaldívar, D., Pérez, M.: Procesamiento digital de imágenes con MATLAB & Simulink. Ra-Ma (2016)

    Google Scholar 

  11. Hossain, M.Z., Amin, M.A., Yan, H.: Rapid feature extraction for optical character recognition. arXiv preprint arXiv:1206.0238 (2012)

  12. Perez, J.-C., Vidal, E., Sanchez, L.: Simple and effective feature extraction for optical character recognition. In: Selected Papers From the 5th Spanish Symposium on Pattern Recognition and Images Analysis: Advances in Pattern Recognition and Applications, Valencia, Spain (1994)

    Google Scholar 

  13. Bokser, M.: Omnidocument technologies. Proc. IEEE 80(7), 1066–1078 (1992)

    Article  Google Scholar 

  14. Trier, O.D., Jain, A.K., Taxt, T., et al.: Feature extraction methods for character recognition-a survey. Pattern Recogn. 29(4), 641–662 (1996)

    Article  Google Scholar 

  15. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

    Google Scholar 

  16. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

  17. Manoj, A., Borate, P., Jain, P., Sanas, V., Pashte, R.: Offline handwriting recognition system using convolutional network (2016)

    Google Scholar 

  18. Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)

    Article  Google Scholar 

  19. de Campos, T.: The Chars74K dataset: character recognition in natural images. University of Surrey, Guildford, Surrey, UK (2012)

    Google Scholar 

  20. LeCun, Y.: The MNIST database of handwritten digits (1998). http://yann.lecun.com/exdb/mnist/

Download references

Acknowledgment

This work has been partially funded by the Spanish MINECO/FEDER through the SmartElderlyCar project (TRA2015-70501-C2-1-R), the DGT through the SERMON project (SPIP2017-02305), and from the RoboCity2030-III-CM project (Robótica aplicada a la mejora de la calidad de vida de los ciudadanos, fase III; S2013/MIT-2748), funded by Programas de actividades I+D (CAM) and cofunded by EU Structural Funds.

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Institute of Engineering and Technology, Autonomous University of Ciudad Juarez, Juarez, Chihuahua, Mexico

    Edwin Antonio Enriquez & Nelly Gordillo

  2. Electronics Department, University of Alcalá (UAH), Alcalá de Henares, Spain

    Luis Miguel Bergasa, Eduardo Romera & Carlos Gómez Huélamo

Authors
  1. Edwin Antonio Enriquez
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nelly Gordillo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Luis Miguel Bergasa
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Eduardo Romera
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Carlos Gómez Huélamo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Luis Miguel Bergasa .

Editor information

Editors and Affiliations

  1. Computer Science Department, Universidad Carlos III de Madrid, Leganés, Madrid, Spain

    Raquel Fuentetaja Pizán

  2. Computer Science Department, Universidad Carlos III de Madrid, Leganés, Madrid, Spain

    Ángel García Olaya

  3. Computer Science Department, Universidad Carlos III de Madrid, Leganés, Madrid, Spain

    Maria Paz Sesmero Lorente

  4. Computer Science Department, Universidad Carlos III de Madrid, Leganés, Madrid, Spain

    Jose Antonio Iglesias Martínez

  5. Computer Science Department, Universidad Carlos III de Madrid, Leganés, Madrid, Spain

    Agapito Ledezma Espino

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Enriquez, E.A., Gordillo, N., Bergasa, L.M., Romera, E., Huélamo, C.G. (2019). Convolutional Neural Network vs Traditional Methods for Offline Recognition of Handwritten Digits. In: Fuentetaja Pizán, R., García Olaya, Á., Sesmero Lorente, M., Iglesias Martínez, J., Ledezma Espino, A. (eds) Advances in Physical Agents. WAF 2018. Advances in Intelligent Systems and Computing, vol 855. Springer, Cham. https://doi.org/10.1007/978-3-319-99885-5_7

Download citation

Publish with us

Policies and ethics

Search

Navigation