WLCSSLearn: learning algorithm for template matching-based gesture recognition systems

Ciliberto, Mathias, Ponce Cuspinera, Luis and Roggen, Daniel (2019) WLCSSLearn: learning algorithm for template matching-based gesture recognition systems. Internatoinal Conference on Activity and Behavior Computing, Spokane, Eastern Washington University, USA, May. 30 - Jun. 2, 2019. Published in: Inoue, Sozo and Rahman Ahad, Atiqur, (eds.) ICIEV-&-ICIVPR 2019. 1 91-96. Institute of Electrical and Electronics Engineers ISBN 9781728107868

[img] PDF - Published Version
Restricted to SRO admin only

Download (176kB)


Template matching algorithms are well suited for gesture recognition, but unlike other machine learning approaches there are no established methods to optimize their parameters. We present WLCSSLearn: an optimization approach for the WarpingLCSS algorithm based on a genetic algorithms. We demonstrate that WLCSSLearn makes the optimization procedure automatic, fast and suitable for new recognition problems even when there is no a-priori knowledge about suitable range of parameter values. We evaluate WLCSSLearn on three different datasets of gestures. We demonstrated that our method increased the accuracy and F1 score up to 20% compared to previous literature.

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Engineering and Design
School of Engineering and Informatics > Informatics
Research Centres and Groups: Sensor Technology Research Centre
Subjects: Q Science > QA Mathematics
Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
T Technology
Related URLs:
Depositing User: Daniel Roggen
Date Deposited: 24 Jun 2019 13:45
Last Modified: 06 Dec 2019 14:45
URI: http://sro.sussex.ac.uk/id/eprint/84471

View download statistics for this item

📧 Request an update