随着虚拟现实技术的飞速发展，人们迫切需要一种自然友好的字符输入方式，于是越来越多的研究人员投入到动态手势的研发当中。本文基于隐马尔可夫模型（HMM）搭建了一套动态手势识别系统。这套系统通过Leap Motion采集动态手势数据，并能够识别36个字母和数字的手势（数字0-9和字母A-Z）。经过大量实验表明，该系统有着很强的鲁棒性，识别单独手势的识别率能够达到93.2%。

With the rapid development of virtual reality technology, more and more researchers are devoting themselves to the research of dynamic gestures recognition. Gesture recognition is a natural and friendly way of human-computer interaction. In this paper, a dynamic gesture recognition system based on Hidden Markov Model (HMM) is built. This system collects dynamic gesture data through Leap Motion and can recognize 36 letters and numbers of gestures (digits 0-9 and A-Z). A lot of experiments show that the system has strong robustness and can recognize individual hands. The recognition rate of potential can reach 93.2%.