A Performance Evaluation of HMM and DTW for Gesture Recognition
It is unclear whether Hidden Markov Models (HMMs) or Dynamic Time Warping (DTW) techniques are more appropriate for gesture recognition. In this paper, we compare both methods using different criteria, with the objective of determining the one with better performance. For this purpose we have created a set of recorded gestures. The dataset used includes many samples of ten different gestures, with their corresponding ground truth obtained with a kinect. The dataset is made public for benchmarking purposes.
The results show that DTW gives higher performance than HMMs, and strongly support the use of DTW.
KeywordsHidden Markov Models Dynamic Time Warping Gesture Recognition Kinect
- 1.Appenrodt, J., Elmezain, M., Al-Hamadi, A., Michaelis, B.: A hidden markov model-based isolated and meaningful hand gesture recognition. International Journal of Electrical, Computer, and Systems Engineering 3, 156–163 (2009)Google Scholar
- 2.ten Holt, G.A., Reinders, M.J.T., Hendriks, E.A.: Multi-Dimensional Dynamic Time Warping for Gesture Recognition. In: Thirteenth Annual Conference of the Advanced School for Computing and Imaging (2007)Google Scholar
- 9.Yang, M.-H., Ahuja, N.: Recognizing Hand Gestures Using Motion Trajectories. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 466–472 (1999)Google Scholar