Gesture recognition on few training data using Slow Feature Analysis and parametric bootstrap

@article{Koch2010GestureRO,
  title={Gesture recognition on few training data using Slow Feature Analysis and parametric bootstrap},
  author={Patrick Koch and Wolfgang Konen and Kristine Hein},
  journal={The 2010 International Joint Conference on Neural Networks (IJCNN)},
  year={2010},
  pages={1-8}
}
Slow Feature Analysis (SFA) has been established as a robust and versatile technique from the neurosciences to learn slowly varying functions from quickly changing signals. Recently, the method has been also applied to classification tasks. Here we apply SFA for the first time to a time series classification problem originating from gesture recognition. The gestures used in our experiments are based on acceleration signals of the Bluetooth Wiimote controller (Nintendo). We show that SFA… CONTINUE READING