[1910.11100] Development of a hand pose recognition system on an embedded computer using CNNs
The results explained before show that our hand pose recognition system can be used for controlling robots, for virtual reality interaction, for human-machine interfaces among others.
Abstract: Demand of hand pose recognition systems are growing in the last years in
technologies like human-machine interfaces. This work suggests an approach for
hand pose recognition in embedded computers using hand tracking and CNNs.
Results show a fast time response with an accuracy of 94.50% and low power