1. Proceedings
  2. I3M
  3. 2020
  4. IWISH
  5. 10.46354/i3m.2020.iwish.007

Handwriting prototype based on FPGA hardware implementation

  • a Ichrak Jeridi, 
  • b Ines Chihi , 
  • c Lilia Sidhom, 
  • d Ernest Nlandu Kamavuako
  • a,b,c Laboratory of energy applications and renewable energy efficiency, University of Tunis El Manar, Tunisia
  • d Centre for Robotics Research, Department of Engineering, Faculty of Natural and Mathematical Sciences, King’s College London
Cite as
Jeridi I., Chihi I., Sidhom L., Kamavuako E.N. (2020). Handwriting prototype based on FPGA hardware implementation. Proceedings of the 9th International Workshop on Innovative Simulation for Healthcare (IWISH 2020), pp. 35-40.
DOI: https://doi.org/10.46354/i3m.2020.iwish.007

Abstract

Handwriting is an important means of communication that can characterize a person and express his academic level, intellectual component, and even the psycho-physical personality of the writer, the temperamental tendencies, and even psychic state. Writing is expressed through motions of the upper limbs and with the availability of different muscle activities, named ElectroMyoGraphy signals (EMG). Forearm EMG driven models can allow reconstruction of individual handwriting. By recovering the coordinates of some shapes generated by a mathematical model allowing the prediction of handwriting on the plane (x, y) from EMG signals, this paper deals with handwriting prototype using hardware implementation based on Field Programmable Gate Arrays (FPGA) of the bi-axis control algorithm to generate human handwriting manuscript in the plan. The presented bi-axis control law is designed in the Xilinx System Generator environment let generate handwriting shapes and complex cursive letters. Comparative analysis between the hardware implementation results generated by the proposed prototype and the recorded data is then presented to show good concordance between the real and the reconstructed data.

References

  1. SchemeE., Fougner A., Stavdahl O., Chan A., and Englehart K. (2010), Examining the adverse effects of limb position on pattern recognition based myoelectric control, in Proc. 32nd Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., Buenos Aires, Argentina, 6337–6340.
  2. Kamavuako E. N., Rosenvang J. C., Bøg M. F., Smidstrup A., Erkocevic E., Niemeier M. J., Jensen
    W, and Farina D. (2013), Influence of the feature space on the estimation of hand grasping force from intramuscular EMG, Biomed. Signal Process. Control, 8,1:1–5
  3. Chihi I., Abdelkrim A. and Benrejeb M. (2012), Analysis of handwriting velocity to identify handwriting process from electromyographic signals, American Journal and Applied Sciences, 9,10:1742-1756.
  4. Chihi I., Abdelkrim A. and Benrejeb M. (2017), Internal model Control to characterize human handwriting motion, International Arab Journal of Information Technology,14,6.
  5. Plamondon R., Alimi A. M., Yergeau P.and Leelerc F. (1993), Modeling velocity profiles of rapid
    movements: a comparative study, Biol. Cybern, Springer, 69:119-128.
  6. Fischer A. and Plamondon R. (2017), Signature Verification Based on the Kinematic Theory of
    Rapid Human Movements,in IEEE Transactions on Human-Machine Systems, 47, 2:169-180.
  7. Zecca M., Micera S., Carrozza M. C. and Dario P. (2002), Control of multifunctional prosthetic
    hands by processing the electromyographic signal, Crit Rev Biomed Eng, 30: 459-485.
  8. Bitzer S. and Van Der Smagt P. (2006), Learning EMG control of a robotic hand: towards active
    prostheses, Proceedings IEEE International Conference on Robotics and Automation, Orlando, 
    2819-2823. 
  9. Schulz S., Pylatiuk C., Reischl M., Martin J., Mikut R., and Bretthauer G. (2005), A hydraulically driven multifunctional prosthetic hand, Robotica, 23,3:293–299.
  10. Sano M., Kosaku T. and Murata Y. (2003), Modeling of human handwriting motion by electromyographic signals on forearm muscles, CCCT’03, Orlando-Florida.
  11. Chihi I., Abdelkrim A.and Benrejeb M. (2015), Multimodel approach to characterize human
    handwriting motion, BiolCybern 110:17–30
  12. Chihi I. and Benrejeb M. (2018), Online Fault Detection Approach of Unpredictable Inputs: Application to Handwriting System, Hindawi, Complexity,2018:1-12.
  13. Chihi I., Sidhom L. and Maamri O. (2018), Robust Handwriting Estimator from Two Forearm Muscles Activities, International Journal of Applied Engineering Research, 13, 23:16213-16219.
  14. Linderman M., Lebedev M.A. and Erlichman J.S. (2009), Recognition of handwriting from
    electromyography, PLoSONE 4:e6791,.
  15. Okorokova E., Lebedev M., Linderman M. and Ossadtchi A. (2015), Adynamical model improves
    reconstruction of handwriting from multichannel electromyographic recordings, Frontiers in
    Neuroscience, 9: 1-15
  16. Li C., Ma Z., Yao L. and Zhang D. (2013), Improvements on emg-based handwriting recognition with dtw algorithm, IEEE Conference Engineering in Medicine and Biology Society (EMBC), of the (IEEE), 2144–2147.
  17. Shilpa K. and Shriramwar S. S. (2009), FPGA-based Controller for a Mobile robot, IEEE International Journal of Computer Science and Information Security, IJCSIS, 3,
  18. Martinez-Prado M., Franco-Gasca A., Herrera-Ruiz G., Soto-Dorantes O. (2013), Multiaxis motion controller for robotic applications implemented on an FPGA, International Journal of Advanced Manufacturing Technology, 67:2367–2376.
  19. Vetter T., Schulz M. (2014), FPGA to Control Power Electronics, Power Electronics Europe, 6: 19-21,.
  20. Di Paolo Emilio M. (2015), Embedded Systems Design for High-Speed Data Acquisition and Control, Springer.
  21. Bresenham J.E. Algorithm for computer control of a digital plotter, IBM Systems Journal, 1965.