Abstract
We utilise the techniques of independent component analysis and principle component analysis to derive an independent set of gestural primitives for visual sign-language, employing existing sign linguistics as a reference point in the feature reduction.
In this way it is possible both to reduce (by several orders of magnitude) the requisite quantity of HMM computation involved in word classification, as well as to significantly improve performance through having transformed the initial classification problem into one of decision fusion. Moreover, the independent and optimally-compact representation of the gestural primitives ensures a maximum of classifier diversity prior to combination.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Starner, T., Pentland, A.: Visual recognition of ASL using hidden Markov models. In: Proc. Int. Workshop Autom. Face Gesture Recogn., Zürich, pp. 189–194 (1995)
Lee, C., Xu, Y.: Online, Interactive Learning of Gestures for Human/Robot Interfaces. In: 1996 IEEE International Conference on Robotics and Automation, Minneapolis, MN, vol. 4, pp. 2982–2987 (1996)
Bowden, R., Sarhadi, M.: A non-linear Model of Shape and Motion for Tracking Finger Spelt ASL. Image and Vision Computing 20(9-10), 597 (2002)
Gibet, S., Braffort, A., Lebourque, T., Forest, F., Gherbi, R., Collet, C., Bourdot, P.: Gesture in Human-Machine Communication. In: Proc. of Gesture Workshop 1996, Springer, London (1997) ISBN 3-540-76094-6
Manduchi, R., Portilla, J.: Independent Component Analysis of Textures. In: Proc. of the IEEE Intern. Conference on Computer Vision, Kerkyra, Greece (September 1999)
Oja, E., Hyvarinen, A., Karhunen, J.: Independent Component Analysis. John Wiley & Sons Inc., Chichester (2001) ISBN: 047140540X
Hyvärinen, A., Oja, E.: Independent Component Analysis: Algorithms and Applications. Neural Networks 13(4-5), 411–430 (2000)
Comon, P.: Independent component analysis, A new concept? IEEE Signal Processing Mag. 36(3) (1994)
Smith, C.: A Guide to B.S.L. Souvenir Press Ltd. (1990) ISBN 0285650831
Funaro, M.: Analysis of Astrophysical Image Data by PCA/ICA. In: European Meeting on I.C.A., Salerno University, Vietri sul Mare (SA), Italy (2002)
Vogler, C., Metaxas, D.: Towards Scalability in ASL Recognition: Breaking Down Signs into Phonemes. In: Gesture Workshop 1999, Gif-sur-Yvette, France (March 1999)
Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Trans. on Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Windridge, D., Bowden, R. (2004). Induced Decision Fusion in Automated Sign Language Interpretation: Using ICA to Isolate the Underlying Components of Sign. In: Roli, F., Kittler, J., Windeatt, T. (eds) Multiple Classifier Systems. MCS 2004. Lecture Notes in Computer Science, vol 3077. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25966-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-25966-4_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22144-9
Online ISBN: 978-3-540-25966-4
eBook Packages: Springer Book Archive