Gesture recognition device based on cross reticulated graphene strain sensors

Perception and recognition of hand gestures have received much attention for their applications in the human–computer fields. The data-glove application in gesture recognition makes it expediently to track the movements of human fingers. Whereas, the development of the data-glove for hand gesture still face numerous technical difficulties, such as the sensitivity, flexible ability, and system integration under low-cost. In this paper, a simple gesture recognition glove system was developed to characterize the sign language, which consists of cross reticulated graphene (CRG) flexible sensors, a multi-channel data acquisition module, and an artificial neural network algorithm. The designed acquisition module has several channels, so that signs from five sensors can be collected and transferred to the intelligent terminal to execute the hand gesture recognition algorithm. Besides, the recognition results suggest that the recognition rate of the neural network for 22 letters in the English alphabet can reach more than 90% and the overall recognition has an over 86% accuracy.