Sawtooth-enhanced bend sensor for gesture recognition

Abstract

Gesture recognition has diverse application prospects in the field of human-computer interaction. Recently, gesture recognition devices based on strain sensors have achieved remarkable results, among which liquid metal materials have considerable advantages due to their high tensile strength and conductivity. To improve the detection sensitivity of liquid metal strain sensors, a sawtooth-enhanced bending sensor is proposed in this study. Compared with the results from previous studies, the bending sensor shows enhanced resistance variation. In addition, combined with machine learning algorithms, a gesture recognition glove based on the sawtooth-enhanced bending sensor is also fabricated in this study, and various gestures are accurately identified. In the fields of human-computer interaction, wearable sensing, and medical health, the sawtooth-enhanced bending sensor shows great potential and can have wide application prospects.