Modelling Visual Appearance of Handwriting

  • Angelo Marcelli
  • Antonio Parziale
  • Adolfo Santoro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8157)


We present an experimental validation of a model of handwriting style that builds upon a neuro-computational model of motor learning and execution. We hypothesize that handwriting style emerges from the concatenation of highly automated writing movements, called invariants, that have been learned by the subject in correspondence to the most frequent sequence of characters the subject is familiar with. We also assume that the actual shape of the ink trace contains enough information to characterize the handwriting style. The experimental results on a data set containing genuine, disguised, and forged (both skilled and naive) documents show that the model is an effective tool for modeling intra-writer and inter-writers variability and provides quantitative estimation of the difference between handwriting styles that is in accordance with the difference in the visual appearance of the handwriting.


handwriting learning and generation model handwriting shape description handwriting analysis 


  1. 1.
    Thomassen, A.J., Teulings, H.L.: Constancy in stationary and progressive handwriting. Acta Psychologica 54(1), 179–196 (1983)CrossRefGoogle Scholar
  2. 2.
    Kawato, M.: Internal models for motor control and trajectory planning. Current Opinion in Neurobiology 9(6), 718–727 (1999)CrossRefGoogle Scholar
  3. 3.
    Grossberg, S., Paine, R.W.: A neural model of cortico-cerebellar interactions during attentive imitation and predictive learning of sequential handwriting movements. Neural Networks 13(8), 999–1046 (2000)CrossRefGoogle Scholar
  4. 4.
    Senatore, R.: The role of Basal ganglia and Cerebellum in Motor Learning: A computational model. PhD Thesis, University of Salerno (March 2012)Google Scholar
  5. 5.
    Senatore, R., Marcelli, A.: A Neural Scheme for Procedural Motor Learning of Handwriting. In: 2012 International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 659–664. IEEE (September 2012)Google Scholar
  6. 6.
    Marcelli, A., Parziale, A., Santoro, A.: Modeling Handwriting Style: a Preliminary Investigation. In: 2012 International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 411–416. IEEE (September 2012)Google Scholar
  7. 7.
    Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct least square fitting of ellipses. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(5), 476–480 (1999)CrossRefGoogle Scholar
  8. 8.
    Bezine, H., Alimi, A.M., Sherkat, N.: Generation and Analysis of Handwriting script with the Beta-elliptic Model. In: Ninth International Workshop on Frontiers in Handwriting Recognition, IWFHR-9 2004, pp. 515–520. IEEE (2004)Google Scholar
  9. 9.
    Cordella, L.P., De Stefano, C., Marcelli, A., Santoro, A.: A New Graph Search Algorithm for Writing Order Recovery. In: ICPR 2010, pp. 23–16 (2010)Google Scholar
  10. 10.
    De Stefano, C., Guadagno, G., Marcelli, A.: A saliency-based segmentation method for online cursive handwriting. International Journal of Pattern Recognition and Artificial Intelligence 18(07), 1139–1156 (2004)CrossRefGoogle Scholar
  11. 11.
    Nocentini, C.: Il problema grafologico. In: Giordano, editore (2006) (in Italian)Google Scholar
  12. 12.
    De Stefano, C., Marcelli, A., Santoro, A.: On-line cursive recognition by ink matching. In: Phillips, J.G., Rogers, D., Ogeil, R.P. (eds.) Proceedings of IGS 2007, pp. 23–37 (2007)Google Scholar
  13. 13.
    De Stefano, C., Garruto, M., Lapresa, L., Marcelli, A.: Using strings for on-line handwriting shape matching: A new weighted edit distance. In: Roli, F., Vitulano, S. (eds.) ICIAP 2005. LNCS, vol. 3617, pp. 1125–1132. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  14. 14.
    Caligiuri, M.P., Mohammed, L.A.: The neuro science of handwriting: applications for forensic document examination. CRC Press (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Angelo Marcelli
    • 1
  • Antonio Parziale
    • 1
  • Adolfo Santoro
    • 1
  1. 1.Natural Computation Laboratory, DIEMUniversity of SalernoFiscianoItaly

Personalised recommendations