Advertisement

Influence of Handshape Information on Automatic Sign Language Recognition

  • Gineke A. ten Holt
  • Marcel J. T. Reinders
  • Emile A. Hendriks
  • Huib de Ridder
  • Andrea J. van Doorn
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5934)

Abstract

Research on automatic sign language recognition (ASLR) has mostly been conducted from a machine learning perspective. We propose to implement results from human sign recognition studies in ASLR. In a previous study it was found that handshape is important for human sign recognition. The current paper describes the implementation of this conclusion: using handshape in ASLR. Handshape information in three different representations is added to an existing ASLR system. The results show that recognition improves, except for one representation. This refutes the idea that extra (handshape) information will always improve recognition. Results also vary per sign: some sign classifiers improve greatly, others are unaffected, and rare cases even show decreased performance. Adapting classifiers to specific sign types could be the key for future ASLR.

Keywords

sign language automatic sign language recognition handshape representation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ong, S.C., Ranganath, S.: Automatic sign language analysis: A survey and the future beyond lexical meaning. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(6), 873–891 (2005)CrossRefGoogle Scholar
  2. 2.
    von Agris, U., Zieren, J., Canzler, U., Bauer, B., Kraiss, K.F.: Recent developments in visual sign language recognition. Univers. Access Inf. Soc. 6(4), 323–362 (2008)CrossRefGoogle Scholar
  3. 3.
    Derpanis, K.G., Wildes, R.P., Tsotsos, J.K.: Hand gesture recognition within a linguistics-based framework. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 282–296. Springer, Heidelberg (2004)Google Scholar
  4. 4.
    Vogler, C., Metaxas, D.: Handshapes and movements: Multiple-channel american sign language recognition. In: Camurri, A., Volpe, G. (eds.) GW 2003. LNCS (LNAI), vol. 2915, pp. 247–258. Springer, Heidelberg (2004)Google Scholar
  5. 5.
    ten Holt, G.A., van Doorn, A.J., de Ridder, H., Reinders, M.J.T., Hendriks, E.A.: Signs in which handshape and hand orientation are either not visible or are only partially visible: What is the consequence for lexical recognition? Sign Language Studies 10(1) (2009)Google Scholar
  6. 6.
    ten Holt, G.A., van Doorn, A.J., de Ridder, H., Reinders, M.J., Hendriks, E.A.: Which fragments of a sign enable its recognition? Sign Language Studies 9(2), 211–239 (2009)CrossRefGoogle Scholar
  7. 7.
    ten Holt, G.A., Arendsen, J., de Ridder, H., van Doorn, A.J., Reinders, M.J., Hendriks, E.A.: Sign language perception research for improving automatic sign and gesture recognition. In: SPIE Human Vision and Electronic Imaging XIV, vol. 7240. SPIE, Bellingham (2009)Google Scholar
  8. 8.
    Lichtenauer, J.F., Hendriks, E.A., Reinders, M.J.: Sign language recognition by combining statistical dtw and independent classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(11), 2040–2046 (2008)CrossRefGoogle Scholar
  9. 9.
    Lichtenauer, J.F., ten Holt, G.A., Reinders, M.J.T., Hendriks, E.A.: Person-independent 3d sign language recognition. In: Sales Dias, M., Gibet, S., Wanderley, M.M., Bastos, R. (eds.) GW 2007. LNCS (LNAI), vol. 5085, pp. 69–80. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  10. 10.
    Hu, M.K.: Visual pattern recognition by moment invariants. IRE Transactions on Information Theory 8(2), 179–187 (1962)CrossRefGoogle Scholar
  11. 11.
    Caridakis, G., Diamanti, O., Karpouzis, K., Maragos, P.: Automatix sign language recognition: vision based feature extraction and probabilistic recognition scheme from multiple cues. In: Proceedings of ACM PETRA (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Gineke A. ten Holt
    • 1
    • 2
  • Marcel J. T. Reinders
    • 1
  • Emile A. Hendriks
    • 1
  • Huib de Ridder
    • 2
  • Andrea J. van Doorn
    • 2
  1. 1.Information and Communication Theory GroupDelft University of TechnologyDelftThe Netherlands
  2. 2.Department of Industrial DesignDelft University of TechnologyDelftThe Netherlands

Personalised recommendations