A robust vision-based hand gesture recognition system for appliance control in smart homes

Adopting a hand gesture based appliance control system would be a virtuous idea for smart homes. However, complexity of the home background makes it challenging to work such systems in real home environments. In this paper, we present developing a robust system which can practically be used in complex backgrounds. The users are required to wear neither wristbands nor long-sleeved garments. In order to achieve this, we use TRS moment invariants combined with Viola-Jones object detection framework. We demonstrate the performance of the system in different complex backgrounds by controlling a pedestal fan.