A New Feature Fusion Method for Gesture Recognition Based on 3D Accelerometer

In this paper, a new feature fusion method for gesture recognition based on single tri-axis accelerometer has been proposed. The process can be explained as follows: firstly, the short-time energy (STE) features are extracted from accelerometer data. Secondly, the hybrid features which combines wavelet packet decomposition with Fast Fourier transform (WPD+FFT) are also extracted. Finally, these two categories features are fused together and the principal component analysis (PCA) is employed to reduce the dimension of the fusion feature. Recognition of the gestures is performed with Support Vector Machine (SVM). The average recognition results of seventeen complex gestures using the proposed fusion feature are 89.89%, which are better than using STE and WPD+FFT. The performance of experimental results show that gesture-based interaction can be used as a novel human computer interaction for consumer electronics and mobile device.