WristPress: Hand Gesture Classification with two-array Wrist-Mounted pressure sensors

Abstract

This paper presents a hand gesture recognition system WristPress based on only the pressure sensors, which can reflect the different pressure changes of different hand gestures. Two arrays of force sensitive resistors (FSRs) are arranged around the wrist to capture the pressure fluctuation with the subtle muscle and tendon movements of different gestures, which can help to identify similar gestures for achieving more functions. For distinguishing more gestures with similar muscle and tendon movements, the temporal features and the spatial features of pressures are selected and designed to characterize the relation of every tiny pressure changes corresponding to the muscle and tendon movements at different positions around the wrist. In the WristPress system, 24 kinds of one-gestures, which cover not only the finger movements but also rotations around the wrist and forearm, are classified with an overall 10-fold cross validation classification accuracy of 97.40%. In addition, the WristPress prototype is non-obtrusive with a small size, and is well suited to existing wearable device forms, such as smart watches and a bracelet that are already mounted on the wrist. Our study shows that the temporal features and the spatial features of these pressures can reflect the the correlation between different pressure sensors can improve the accuracy of the hand gesture classification, and the kNN classifier has the best classification accuracy performance 97.40% with a low time complexity.