Information Expression Oriented toward the Hearing-Impaired Based on Sign Language Video Synthesis  

面向听障人士基于手语视频合成的信息表达(英文)

作　　者：王茹 王立春 孔德慧 尹宝才 

机构地区：[1]Beijing Key Laboratory of Multimedia and Intelligent Software Technology,College of Computer Science and Technology,Beijing University of Technology

出　　处：《China Communications》2011年第1期139-144,共6页中国通信（英文版）

基　　金：supported by the National Natural Science Foundation of China(Nos.60825203,60973056,60973057,U0935004);National Technology Support Project(2007BAH13B01);Beijing Municipal Natural Science Foundation(4102009);Scientific Research Common Program of Beijing Municipal Commission of Education(KM200710005023);PHR(IHLB)

摘　　要：Among the human users of the Internet of Things,the hearing-impaired is a special group of people for whom normal information expression forms,such as voice and video are unaccessible,and most of them have some difficulty in understanding information in text form.The hearing-impaired are accustomed to receiving information expressed in sign language.For this situation,a new information expression form for the Internet of Things oriented toward the hearing-impaired is proposed in this paper,and the new expression is based on sign language video synthesis.Under the sign synthesis frame,three modules are necessary:constructing database,searching for appropriate sign language video units and transition units,and generating interpolated frames.With this method,text information could be transformed into sign language expression for the hearing-impaired.Among the human users of the Internet of Things, the hearing-impaired is a special group of people for whom normal information expression forms, such as voice and video are unaccessible, and most of them have some difficulty in under- standing information in text form. The hearing- impaired are accustomed to receiving information expressed in sign language. For this situation, a new information expression form for the Internet of Things oriented toward the hearing-impaired is pro- posed in this paper, and the new expression is based on sign language video synthesis. Under the sign synthesis frame, three modules are necessary： constructing database, searching for appropriate sign language video units and transition units, and gener- ating interpolated frames. With this method, text in- formation could be transformed into sign language expression for the hearing-impaired.

关 键 词：information express sign language video synthesis Internet of Things sign language anima- tion 

分 类 号：TN919.8[电子电信—通信与信息系统]