A wearable hand gesture recognition device based on acoustic measurements at wrist.

This paper investigates hand gesture recognition from acoustic measurements at wrist for the development of a low-cost wearable human-computer interaction (HCI) device. A prototype with 5 microphone sensors on human wrist is benchmarked in hand gesture recognition performance by identifying 36 gestures in American Sign Language (ASL). Three subjects were recruited to perform over 20 trials for each set of hand gestures, including 26 ASL alphabets and 10 ASL numbers. Ten features were extracted from the signal recorded by each sensor. Support Vector Machine (SVM), Decision Tree (DT), K-Nearest Neighbors (kNN), and Linear Discriminant Analysis (LDA) were compared in classification performance. Among which, LDA offered the highest average classification accuracy above 80%. Based on these preliminary results, our proposed technique has exhibited a promising means for developing a low-cost HCI.