Research on Sign News Management System

摘要

In recent years, more and more television stations in China are providing sign language news reports to assist the deaf and mute to watch the news programs on TV. As the sign language videos are becoming enormous, how to manage them remains formidable. Our objective is to present a method to manage the sign video resource and implement a content-based analysis and retrieval system. The contributions are: (i) we present a method to robustly track the hands' motion by a optic flow and clustering method;(ii) we propose a feature expression method to express signing sequences which includes the trajectory of both hands, the hand shape and orientation, and properly models the case of hands touching; (iii) we propose a matching method between the input video signed by the deaf people using camera and the video segments in database. The experiment results show that our method performs well and is fairly effective and deserves popularization.