A Hybrid Grammar-Based Approach for Learning and Recognizing Natural Hand Gestures

Authors

  • Amir Sadeghipour Bielefeld University
  • Stefan Kopp Bielefeld University

DOI:

https://doi.org/10.1609/aaai.v28i1.9023

Keywords:

Machine Learning, Classification, Gesture recognition, Feature-based Stochastic Context-free Grammar

Abstract

In this paper, we present a hybrid grammar formalism designed to learn structured models of natural iconic gesture performances that allow for compressed representation and robust recognition. We analyze a dataset of iconic gestures and show how the proposed Feature-based Stochastic Context-Free Grammar (FSCFG) can generalize over both structural and feature-based variations among different gesture performances.

AAAI 2014 Proceedings Cover

Downloads

Published

2014-06-21

How to Cite

Sadeghipour, A., & Kopp, S. (2014). A Hybrid Grammar-Based Approach for Learning and Recognizing Natural Hand Gestures. Proceedings of the AAAI Conference on Artificial Intelligence, 28(1). https://doi.org/10.1609/aaai.v28i1.9023

Issue

Vol. 28 No. 1 (2014): Twenty-Eighth AAAI Conference on Artificial Intelligence

Section

Main Track: Novel Machine Learning Algorithms