Since computers have become more fundamental in society, there
has been an increase in demand for Human Computer Interaction. Hence, there has
been growing interest in the development of new approaches in Human Computer
Interaction. Gesture recognition is an important part of Human Computer
Interaction and has a wide variety of applications like gaming and virtual
reality. Previous work and approaches use sensors that are worn by the user or
cameras that require proper light to identify gestures. In this paper, we
introduce a finger gesture recognition system by using a WiFi device
without requiring any cameras or the user to wear any sensors. Our system uses
Channel State Information (CSI) from a WiFi device
and identifies small movements of finger gestures by analyzing the unique
patterns of Channel State Information. We also incorporate an environmental
noise removal mechanism to mitigate any noise cause due to environmental
changes. Our experimental evaluation shows that our system can achieve about
80% accuracy and is robust to individual diversity. Moreover our results show
that our system is immune to NLOS scenarios.

Categories: Articles

x

Hi!
I'm Garrett!

Would you like to get a custom essay? How about receiving a customized one?

Check it out