Non-linear Distance-based Semi-supervised Multi-class Gesture Recognition
Husam Al-Behadili, Arne Grumpe, Christian Wöhler
2016
Abstract
The automatic recognition of gestures is important in a variety of applications, e.g. human-machine-interaction. Commonly, different individuals execute gestures in a slightly different manner and thus a fully labelled dataset is not available while unlabelled data may be acquired from an on-line stream. Consequently, gesture recognition systems should be able to be trained in a semi-supervised learning scenario. Additionally, real-time systems and large-scale data require a dimensionality reduction of the data to reduce the processing time. This is commonly achieved by linear subspace projections. Most of the gesture data sets, however, are non-linearly distributed. Hence, linear sub-space projection fails to separate the classes. We propose an extension to linear subspace projection by applying a non-linear transformation to a space of higher dimensional after the linear subspace projection. This mapping, however, is not explicitly evaluated but implicitly used by a kernel function. The kernel nearest class mean (KNCM) classifier is shown to handle the non-linearity as well as the semi-supervised learning scenario. The computational expense of the non-linear kernel function is compensated by the dimensionality reduction of the previous linear subspace projection. The method is applied to a gesture dataset comprised of 3D trajectories. The trajectories were acquired using the Kinect sensor. The results of the semi-supervised learning show high accuracies that approach the accuracy of a fully supervised scenario already for small dimensions of the subspace and small training sets. The accuracy of the semi-supervised KNCM exceeds the accuracy of the original nearest class mean classifier in all cases.
References
- Al-Behadili, H., Wöhler, C., and Grumpe, A. (2014). Semisupervised learning of emblematic gestures. ATAUTOMATISIERUNGSTECHNIK, 62(10):732-739.
- Al-Behadili, H., Wöhler, C., and Grumpe, A. (2015). NonLinear Distance Based Large Scale Data Classifications. In 3'rd International conference on image Information Processing (ICIIP), page In Press. IEEE.
- Altman, N. S. (1992). An introduction to kernel and nearestneighbor nonparametric regression. The American Statistician, 46(3):175-185.
- Bhuyan, M., Bora, P., and Ghosh, D. (2008). Trajectory guided recognition of hand gestures having only global motions. International Journal of Computer Science, Fall.
- Boiman, O., Shechtman, E., and Irani, M. (2008). In defense of nearest-neighbor based image classification.
- In Computer Vision and Pattern Recognition, 2008.
- CVPR 2008. IEEE Conference on, pages 1-8. IEEE.
- Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. Information Theory, IEEE Transactions on, 13(1):21-27.
- Elmezain, M., Al-Hamadi, A., Rashid, O., and Michaelis, B. (2009). Posture and Gesture Recognition for Human-Computer Interaction. In Jayanthakumaran, K., editor, Advanced Technologies, pages 415-440. InTech, Rijeka, Croatia.
- Fothergill, S., Mentis, H., Kohli, P., and Nowozin, S. (2012). Instructing people for training gestural interactive systems. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pages 1737-1746. ACM.
- Guillaumin, M., Mensink, T., Verbeek, J., and Schmid, C. (2009). Tagprop: Discriminative metric learning in nearest neighbor models for image auto-annotation. In Computer Vision, 2009 IEEE 12th International Conference on, pages 309-316. IEEE.
- Kung, S. Y. (2014). Kernel Methods and Machine Learning. Cambridge University Press.
- Mensink, T., Verbeek, J., Perronnin, F., and Csurka, G. (2013a). Distance-based image classification: Generalizing to new classes at near-zero cost. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(11):2624-2637.
- Mensink, T., Verbeek, J., Perronnin, F., and Csurka, G. (2013b). Large scale metric learning for distancebased image classification on open ended data sets. In Advanced Topics in Computer Vision, pages 243-276. Springer.
- Richarz, J. and Fink, G. A. (2011). Visual recognition of 3d emblematic gestures in an hmm framework. Journal of Ambient Intelligence and Smart Environments, 3(3):193-211.
- Schneider, P., Biehl, M., and Hammer, B. (2009). Adaptive relevance matrices in learning vector quantization. Neural Computation, 21(12):3532-3561.
- Theodoridis, S., Pikrakis, A., Koutroumbas, K., and Cavouras, D. (2010). Introduction to Pattern Recognition: A Matlab Approach. Academic Press.
- Webb, A. R. (2003). Statistical pattern recognition. John Wiley & Sons.
- Yoon, H.-S., Soh, J., Bae, Y. J., and Yang, H. S. (2001). Hand gesture recognition using combined features of location, angle and velocity. Pattern recognition, 34(7):1491-1501.
- Zhu, X. and Goldberg, A. B. (2009). Introduction to Semisupervised Learning. Synthesis lectures on artificial intelligence and machine learning. Morgan & Claypool Publishers.
Paper Citation
in Harvard Style
Al-Behadili H., Grumpe A. and Wöhler C. (2016). Non-linear Distance-based Semi-supervised Multi-class Gesture Recognition . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 280-286. DOI: 10.5220/0005674102800286
in Bibtex Style
@conference{visapp16,
author={Husam Al-Behadili and Arne Grumpe and Christian Wöhler},
title={Non-linear Distance-based Semi-supervised Multi-class Gesture Recognition},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={280-286},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005674102800286},
isbn={978-989-758-175-5},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)
TI - Non-linear Distance-based Semi-supervised Multi-class Gesture Recognition
SN - 978-989-758-175-5
AU - Al-Behadili H.
AU - Grumpe A.
AU - Wöhler C.
PY - 2016
SP - 280
EP - 286
DO - 10.5220/0005674102800286