摘要
随着计算机技术的发展,视频数据的容量以几何级数增长。如何在海量视频数据库中快速地检索到所需视频成为热门的研究课题。本文提出了一种基于反馈式神经网络的视频检索算法,对视频进行基于内容的分析和检索。实验表明用该方法检索的准确度比用基于关键帧的视频检索方法平均提高4%以上。
With the development of IT technology, the volume of video data is increasing in geometric progression. How to rapidly capture the wanted video data at the sea video database is currently the hot research topic. This discourse advances such a video retrieval method based on the artificial nerve network. The method will perform the content -based ana/ysis and retrieval for the video data. The experiment shows that the accuracy of this method is improved and is increased by 4% on average compared with the key frame - based video retrieval method.
出处
《九江学院学报》
2009年第6期11-14,共4页
JOurnal of Jiujiang University :Social Science Edition
关键词
视频检索
相关反馈
神经网络
Video retrieval
relevant feedback
neural network