Skip to main content

Volume 16 Supplement 2

Global Software Engineering

Comparative evaluation of static gesture recognition techniques based on nearest neighbor, neural networks and support vector machines

Abstract

It is a common behavior for human beings to use gestures as a means of expression, as a complement to speaking, or as a self-contained communication mode. In the field of Human–Computer Interaction, this behavior can be adopted to build alternative interfaces, aiming to ease the relationship between the human element and the computational element. Currently, various gesture recognition techniques are described in the technical literature; however, the validation studies of these techniques are usually performed isolatedly, which complicates comparisons between them. To reduce this gap, this work presents a comparison between three well-established techniques for static gesture recognition, using Nearest Neighbor, Neural Networks, and Support Vector Machines as classifiers. These classifiers evaluate a common dataset, acquired from an instrumented glove, and generate results for precision and performance measurements. The results obtained show that the classifier implemented as a Support Vector Machine presented the best generalization, with the highest recognition rate. In terms of performance, all methods presented evaluation times fast enough to be used interactively. Finally, this work identifies and discusses a set of relevant criteria that must be observed for the training and evaluation steps, and its relation to the final results.

References

  1. Hewett TT, Baecker R, Card S, et al (1997) Curricula for human–computer interaction. ACM SIGCHI. http://old.sigchi.org/cdg/. Accessed 5 September 2009

  2. Myers BA (1998) A brief history of human–computer interaction technology. ACM Interact 5(2):44–54. doi:10.1145/274430.274436

    Article  Google Scholar 

  3. Wilson AD, Izadi S, Hilliges O, et al (2008) Bringing physics to the surface. In: Proc 21st annu ACM symp user interface softw technol, pp 67–76. doi:10.1145/1449715.1449728

  4. Rick J, Rogers Y (2008) From DigiQuilt to DigiTile: Adapting educational technology to a multi-touch table. In: 3rd IEEE int workshop horiz interact hum comput syst, pp 73–80. doi:10.1109/TABLETOP.2008.4660186

  5. Tani BS, Maia RS, Wangenheim Av (2007) A gesture interface for radiological workstations. In: Proc 20th int symp comput-based med syst, pp 27–32. doi:10.1109/CBMS.2007.6

  6. Xu D, Yao W, Zhang Y (2006) Hand gesture interaction for virtual training of SPG. In: Proc 16th int conf artif real telexistence, pp 672–676. doi:10.1109/ICAT.2006.68

  7. Deller M, Ebert A, Bender M, et al (2006) Flexible gesture recognition for immersive virtual environments. In: Proc int conf inf vis, pp 563–568. doi:10.1109/IV.2006.55

  8. LaViola JJ (1999) A survey of hand posture and gesture recognition techniques and technology. Technical Rep CS-99-11, Brown University

  9. Iwai Y, Shimizu H, Yachida M (1999) Real-time context-based gesture recognition using hmm and automaton. In: Proc int workshop recognit analysis track faces gestures real-time syst, p 127. doi:10.1109/RATFG.1999.799235

  10. Lee C, Ghyme S, Park C, et al (1998) The control of avatar motion using hand gesture. In: Proc ACM symp virtual real softw technol, pp 59–65. doi:10.1145/293701.293709

  11. Kjellström H, Romero J, Kragić D (2008) Visual recognition of grasps for human-to-robot mapping. In: IEEE/RSJ int conf intell robot syst, pp 3192–3199. doi:10.1109/IROS.2008.4650917

  12. Kim J-H, Roh Y-W, Shin J-H, et al (2005) Performance evaluation of a hand gesture recognition system using fuzzy algorithm and neural network for post PC platform. In: Int workshop soft comput appl, pp 129–138. doi:10.1007/11676935_16

  13. Bowman DA, Kruijff E, LaViolla JJ, et al. (2005) 3D user interfaces: Theory and practice. Addison-Wesley, Boston

    Google Scholar 

  14. Fausett L (1994) Fundamentals of neural networks: Architectures, algorithms, and applications. Prentice-Hall, Upper Saddle River

    Google Scholar 

  15. Stergiopoulou E, Papamarkos N (2009) Hand gesture recognition using a neural network shape fitting technique. Eng Appl Artif Intell 22(8):1141–1158. doi:10.1016/j.engappai.2009.03.008

    Article  Google Scholar 

  16. Bailador G, Roggen D, Tröster G, et al (2007) Real time gesture recognition using continuous time recurrent neural networks. In: Proc 2nd int conf body area netw, pp 1–8

  17. Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge

    Book  Google Scholar 

  18. Ren Y, Zhang F (2009) Hand gesture recognition based on MEB-SVM. In: Proc int conf embed softw syst, pp 344–349. doi:10.1109/ICESS.2009.21

  19. Liu Y, Gan Z, Sun Y (2008) Static hand gesture recognition and its application based on support vector machines. In: Proc int conf softw eng artif intell netw parallel distrib comput, pp 517–521. doi:10.1109/SNPD.2008.144

  20. Chen Y-T, Tseng K-T (2007) Developing a multiple-angle hand gesture recognition system for human machine interactions. In: 33rd annu conf IEEE ind electron soc, pp 489–492. doi:10.1109/IECON.2007.4460049

  21. Meng H, Pears N, Bailey C (2007) A human action recognition system for embedded computer vision application. In: Conf comput vis pattern recognit, pp 1–6. doi:10.1109/CVPR.2007.383420

  22. Duda RO, PE Hart, Stork DG (2000) Pattern classification. Wiley-Interscience, New York

    Google Scholar 

  23. Athitsos V, Stefan A, Alon J, et al (2008) Translation and scale-invariant gesture recognition in complex scenes. In: Proc 1st int conf pervasive technol relat assist env, pp 1–8. doi:10.1145/1389586.1389595

  24. Ziaie P, Müller T, Foster ME, et al (2008) Using a naïve Bayes classifier based on k-nearest neighbors with distance weighting for static hand-gesture recognition in a human-robot dialog system. In: Proc 13th int CSI comput conf

  25. Tarrataca L, Santos AC, Cardoso JMP (2009) The current feasibility of gesture recognition for a smartphone using J2ME. In: Proc ACM symp appl comput, pp 1642–1649. doi:10.1145/1529282.1529652

  26. Wang RY, Popović J (2009) Real-time hand-tracking with a color glove. In: Int conf comput graphics interact tech, pp 1–8. doi:10.1145/1576246.1531369

  27. 5DT data glove ultra series. http://www.5dt.com/downloads/dataglove/ultra/5DTDataGloveUltraDatasheet.pdf. Accessed 7 November 2009

  28. Sarle WS (1997) Neural network FAQ. ftp://ftp.sas.com/pub/neural/FAQ.html. Accessed 2 November 2009

  29. Tani BS, Nobrega T, Santos TR, et al (2006) Generic visualization and manipulation framework for three-dimensional medical environments. In: Proc 19th int symp comput-based med syst, pp 27–31. doi:10.1109/CBMS.2006.91

  30. Silva AFB, Nobrega THC, Carvalho DDB, et al (2009) Framework for interactive medical imaging applications. In: Colloq comput Brazil. INRIA coop adv chall, pp 126–129

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Aldo von Wangenheim.

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License ( https://creativecommons.org/licenses/by/2.0 ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and permissions

About this article

Cite this article

Savaris, A., von Wangenheim, A. Comparative evaluation of static gesture recognition techniques based on nearest neighbor, neural networks and support vector machines. J Braz Comput Soc 16, 147–162 (2010). https://doi.org/10.1007/s13173-010-0009-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13173-010-0009-z

Keywords