摘要
为促进聋哑人与正常人之间的交流，本文设计并实现了一个聋哑人辅助教学系统．该系统的功能是能够在文本的驱动下实时合成一个有表情，有口型，有手势动作的三维虚拟“图形人”．对于用户任意输入的一段文本，系统首先将其切分成词的序列，然后顺次驱动“图形人”根据当前词蕴涵的感情色彩做出相应的表情，同时作出该词发音时的相应口型并打出对应于当前词的哑语手势．本系统可以直接应用于聋哑人辅助教学．
In order to enhance the communication between the deaf mute and the normal, a deaf mute aid education system is designed and implemented in this paper. The function of this system is synthesizing a 3 D virtual“graphic human” which has facial expressions, mouth shapes and hand gestures in real time by the driving of the text. Base on a paragraph of random text input by the user, this system segments the text into a sequence of separate words, and then drives the “graphic human” making expression based on the emotions implied by the current word, making mouth shape at the same time and making hand gestures according to the hand gesture language. This system can be directly used in the deaf mute aid education.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
1998年第5期400-408,共9页
Journal of Computer-Aided Design & Computer Graphics
关键词
聋哑教育
CAI
唇动合成
手语合成
body language, text driven, facial expression synthesis, lip motion synthesis, hand gesture language synthesis
