Author: Bacher, R.
Paper Title Page
MOPHA011 Improving Gesture Recognition with Machine Learning: A Comparison of Traditional Machine Learning and Deep Learning 214
  • R. Bacher
    DESY, Hamburg, Germany
  Meaningful gesturing is important for an intuitive human-machine communication. This paper deals with methods suitable for identifying different finger, hand and head movements using supervised machine learning algorithms. On the one hand it discusses an implementation based on the k-nearest neighbor classification algorithm (traditional machine learning approach). On the other hand it demonstrates the classification potential of a convolutional neural network (deep learning approach). Both methods are capable of distinguishing between fast and slow, short and long, up and down, or right and left linear as well as clockwise and counterclockwise circular movements. The details of the different methods with respect to recognition accuracy and performance will be presented.  
poster icon Poster MOPHA011 [0.927 MB]  
DOI • reference for this paper ※  
About • paper received ※ 27 August 2019       paper accepted ※ 08 October 2019       issue date ※ 30 August 2020  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)