A Novel Method for Data Glove-Based Dynamic Gesture Recognition

The correctness and robustness of gesture recognition have a significant effect on subsequent operations. In this paper, an algorithm is proposed to obtain angle change data of finger joints by means of data glove, and then the process of dynamic gesture recognition is carried out by fitting the data to curves and calculating the Hausdorff distance between them. The experimental results show that the recognition rate of the method can reach 98% when the number of gesture categories are ten. The algorithm has low computational complexity and high efficiency, which can guarantee the correctness and robustness of gesture recognition.