Gesthaar: An accelerometer-based gesture recognition method and its application in NUI driven pervasive healthcare

@article{Khan2012GesthaarAA,
  title={Gesthaar: An accelerometer-based gesture recognition method and its application in NUI driven pervasive healthcare},
  author={Mridul Khan and Sheikh Iqbal Ahamed and Miftahur Rahman and Ji-Jiang Yang},
  journal={2012 IEEE International Conference on Emerging Signal Processing Applications},
  year={2012},
  pages={163-166}
}
Natural user interfaces that detect gestures from acceleration data require fast and highly accurate signal matching algorithms to provide fluid interaction. In this paper, we contribute a novel system that uses Haar transform and Support Vector Machines for accelerometer-based gesture recognition. We benchmarked it using the uWave gesture library and found around 99% recognition accuracy after tenfold cross validation. Our method is better than those currently in the literature in terms of… CONTINUE READING
Highly Cited
This paper has 33 citations. REVIEW CITATIONS

7 Figures & Tables

Topics

Statistics

0102030201620172018
Citations per Year

Citation Velocity: 6

Averaging 6 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.