Abstract:

Leap Motion gesture recognition has an unstable recognition phenomenon at the edge of recognition area and the occlusion of finger. This paper proposes a Leap Motion gesture interaction level correction method. The method analyzes the recognition error of Leap Motion by real-time contrast threshold method, and uses the layered correction algorithm to correct the position of the human hand and solve the identification instability phenomenon in the process of human interaction. Through the analysis of the experiment, 75% participants are satisfied with the experimental interaction, 80% participants believe that the method is more accurate, and the recognition accuracy of the interactive content exceeds 89%, which fully proves that the method can improve the recognition accuracy and improve the user experience of Leap Motion.

Key words: Human-Computer Interaction（HCI）, Leap Motion, hierarchical movement, user study

摘要：

Leap Motion手势识别在识别区域边缘和手指遮挡部位存在识别不稳定的现象。提出了一种Leap Motion手势交互层次校正方法。该方法通过实时对比阈值方式分析Leap Motion的识别错误，并采用层次化的校正算法校正人手位置，解决人手交互过程中的识别不稳定现象。通过对实验进行分析，75%参与者对实验交互方式满意，80%参与者认为该方法更精确，且交互内容识别精度超过89%，充分证明了该方法能够提高Leap Motion的识别准确率，提升用户体验。

关键词: 人机交互（HCI）, Leap Motion, 层次化运动, 用户调研