多层DGMM识别器在中国手语识别中的应用

手语是聋人使用的语言，是由手形动作辅之以表情姿势由符号构成的比较稳定的表达系统 ，是一种靠动作/视觉交际的语言.手语识别的研究目标是让机器“看懂”聋人的语言.手 语识别和手语合成相结合，构成一个“人-机手语翻译系统”，便于聋人与周围环境的交 流.手语识别问题是动态手势信号即手语信号的识别问题.考虑到系统的实时性及识别效率， 该系统选取Cyberglove型号数据手套作为手语输入设备，采用DGMM(dynamic Gaussian mixt ure model)作为系统的识别技术，并根据中国手语的具体特点，在识别模块中选取了多层识 别器，可识别中国手语字典中的274个词条，识别率为97.4%.与基于单个DGMM的识别系统比 较，这种模型的识别精度与单个DGMM模型的识别精度基本相同，但其识别速度比单个DGMM的 识别速度有明显的提高.

A Hierarchical DGMM Recognizer for Chinese Sign Language Recognition

Sign language is the language used by the deaf, which is a comparatively s teadier expressive system composed of signs corresponding to postures and motion s assisted by facial expression. And it is a language communicated by motion/vis ion. The objective of sign language recognition research is to "see" the langu age of the deaf. The integration of sign language recognition and sign languag e synthesis jointly comprises a "human-computer sign language interpreter", w hich facilitates the interaction between deaf people and their surrounding s. The issue of sign language recognition is to recognize dynamic gesture signal , that is, to recognize sign language signal. Considering the speed and performa nce of the recognition system, Cyberglove is selected as gesture input device in sign language recognition system, DGMM (dynamic Gaussian mixture model) is used as recognition technique, and hierarchical recognizer is used in recognizing mo dule, which can recognize 274 sign language words coming from the dictionary of Chinese sign language with an accuracy of 97.4%, based on Chinese sign language' s own characteristic. Compared with the recognition system based on single-DGMM recognizer, the recognition rate of hierarchical DGMM recognizer is nearly equa l to that of single-DGMM recognizer, but its recognition speed is apparently mu ch faster than that of single-DGMM recognizer.