Abstract
In these days, “early recognition” of gesture patterns has been studied by many researchers. Early recognition is a method to make a decision of gesture recognition at the beginning part of it. In traditional method, the key postures for a gesture are utilized for recognition and early recognition is performed frame-by-frame. However, this method has a problem that computational time in recognition processing increases in proportion to size of posture database. If the processing time becomes longer, some input frames will be ignored from the processing. It results in lower recognition accuracy. In this paper, we introduce a hash-based approach to search the posture database. It realizes real-time processing, and keep high performance of recognition.
Similar content being viewed by others
Notes
This evaluation is defined by,
$$ \frac{\hbox {\# \; of \; required \; frames}}{\hbox {\# of all frames}}\times 100\,(\%) $$(6)We utilized this evaluation when the recognition result is output in the gesture. Therefore, the lower value this evaluation takes, the earlier the system can output the recognition result.
References
Starner T, Weaver J, Pentland A (1998) Real-time American sign language recognition using desk and wearable computer based video. IEEE Trans Pattern Anal Mach Intell 20:12
Nickel K, Stiefelhagen R (2007) Visual recognition of pointing gestures for humanrobot interaction. Image Vision Comput 25:1875–1884
Elmezain M, Al-hamadi A, Appenrodt J, Michaelis B (2008) A hidden Markov model-based continuous gesture recognition system for hand motion trajectory. CD-ROM Proc Int Conf Pattern Recognit
Mori A, Uchida S, Kurazume R, Taniguchi R, Hasegawa T, Sakoe H (2012) Early recognition and prediction of gestures. Proc Int Conf Pattern Recognit 3 of 4:560–563
Uchida S, Amamoto K (2008) Early recognition of sequential patterns by classifier combination. CD-ROM Proc Int Conf Pattern Recognit
Kawashima M, Shimada A, Taniguchi R (2012) Early recognition of gesture patterns using self-organizing map. The fifth joint workshop on machine perception and robotics
Indyk P, Motwani R (1998) Approximate nearest neighbor: towards removing the curse of dimensionality. ACM symposium on theory of computing (STOC)
Kohonen T (1989) Self-organization and associative memory. Springer, Berlin
Kohonen T (1995) Self-organizing maps. Springer, Berlin
Microsoft Kinect SDK for Windows. http://www.microsoft.com/en-us/kinectforwindows/
Acknowledgments
This work was supported by KAKENHI Grant-in-Aid for Young Scientists (A) (23680018).
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the 17th International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–21, 2012.
About this article
Cite this article
Ko, Y., Shimada, A., Nagahara, H. et al. Hash-based early recognition of gesture patterns. Artif Life Robotics 17, 476–482 (2013). https://doi.org/10.1007/s10015-012-0085-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-012-0085-6