Research on a novel gesture recognition device

Abstract

In order to effectively detect the input gesture information, a new type of capacitive sensing technology, which is of a low power consumption, low cost but high resolution non-contact sensing technology, is adopted. When our finger gets close to the metal plate, it will cause the change of the capacitance value of the metal plate to the ground. That value can be converted into 28-bit binary data for output. The microprocessor is equipped with the IIC interface for acquisition and processing of the output data. Because a variety of gestures produce different capacitance values, their output varies. After many times of training and machine learning, different gestures can be identified. The test results show the rate of different gestures recognition is over 99%, which can be applicable in human-computer interaction equipment.