Deep Learning Networks for Off-Line Handwritten Signature Recognition

  • Bernardete Ribeiro
  • Ivo Gonçalves
  • Sérgio Santos
  • Alexander Kovacec
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7042)

Abstract

Reliable identification and verification of off-line handwritten signatures from images is a difficult problem with many practical applications. This task is a difficult vision problem within the field of biometrics because a signature may change depending on psychological factors of the individual. Motivated by advances in brain science which describe how objects are represented in the visual cortex, advanced research on deep neural networks has been shown to work reliably on large image data sets. In this paper, we present a deep learning model for off-line handwritten signature recognition which is able to extract high-level representations. We also propose a two-step hybrid model for signature identification and verification improving the misclassification rate in the well-known GPDS database.

Keywords

Deep Learning Generative Models Signature Recognition 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ackley, D., Hinton, G., Sejnowski, T.: A learning algorithm for Boltzmann Machines. Science 9(1), 147–169 (1985)Google Scholar
  2. 2.
    Armand, S., Blumenstein, M., Muthukkumarasamy, V.: Off-line signature verification using an enhanced modified direction feature with single and multi-classifier approaches. IEEE Computational Intelligence Magazine 2(2), 18–25 (2007)CrossRefGoogle Scholar
  3. 3.
    Bengio, Y.: Learning deep architectures for AI. Foundations and Trends in Machine Learning 2(1), 1–127 (2009)CrossRefMATHGoogle Scholar
  4. 4.
    Bengio, Y., Delalleau, O.: Justifying and generalizing contrastive divergence. Neural Computation 21(6), 1601–1621 (2009)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Bluemenstein, M., Liu, X.Y.: A modified direction feature for cursive character recognition. In: IEEE-IJCNN, pp. 2983–2987 (2004)Google Scholar
  6. 6.
    Ferrer, M.A., Alonso, J.B., Travieso, C.M.: Off-line geometric parameters for automatic signature verification using fixed-point arithmetic. IEEE Trans. on Pattern Analysis and Intelligence 27(6), 993–997 (2005)CrossRefGoogle Scholar
  7. 7.
    Gader, P.D., Mohamed, M., Chiang, J.H.: Handwritten word recognition with character and inter-character neural networks. IEEE Trans. on Sys., Man and Cyber. - Part B: Cybernetics 27(1), 158–164 (1997)CrossRefGoogle Scholar
  8. 8.
    Gonçalves, I., Santos, S.: Off-line signatures verification system. Tech. Rep. trp-#10/11, University of Coimbra, Portugal (2011)Google Scholar
  9. 9.
    Hinton, G.E.: Learning multiple layers of representation. Trends in Cognitive Sciences 11, 428–434 (2007)CrossRefGoogle Scholar
  10. 10.
    Hinton, G.E., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Computation 18, 1527–1554 (2006)MathSciNetCrossRefMATHGoogle Scholar
  11. 11.
    Larochelle, H., Bengio, Y., Louradour, J., Lamblin, P.: Exploring strategies for training deep neural networks. J. of Machine Learning Research 10, 1–40 (2009)MATHGoogle Scholar
  12. 12.
    Longcamp, M., Boucard, C., Gilhodes, J.C., Anton, J.L., Roth, M., Nazarian, B., Velav, J.L.: Learning through hand- or typewriting influences visual recognition of new graphic shapes: Behavioral and functional imaging evidence. Science Journal of Cognitive Neuroscience 20, 802–815 (2008)CrossRefGoogle Scholar
  13. 13.
    Lv, H., Wang, W., Wang, C., Zhuo, Q.: Off-line chinese signature verification based on support vector machines. Pattern Recognition Letters 26, 2390–2399 (2005)CrossRefGoogle Scholar
  14. 14.
    Nguyen, V., Blumenstein, M., Vallipuram, M., Leedham, G.: Off-line signature verification using enhanced modified direction features in conjunction with neural classifiers and support vector machines. In: IEEE-ICDAR, pp. 1300–1304 (2009)Google Scholar
  15. 15.
    Yu, K., Xu, W., Gong, Y.: Deep learning with kernel regularization for visual recognition. In: Neural Information Processing Systems, NIPS (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Bernardete Ribeiro
    • 1
  • Ivo Gonçalves
    • 1
  • Sérgio Santos
    • 1
  • Alexander Kovacec
    • 2
  1. 1.CISUC, Department of Informatics EngineeringUniversity of CoimbraPortugal
  2. 2.Department of MathematicsUniversity of CoimbraPortugal

Personalised recommendations