Existing video text segmentation algorithms are generally based on a single attribute of video texts.
现有视频文字分割算法一般只利用了视频文字某一方面的特性。
In this thesis, firstly, video frame segmentation algorithm of multi-modal information based on artificial text and visual characteristics is proposed.
本文首先给出一种基于人工文本与视觉特征的多模态信息视频帧分割算法。
In this paper, news story segmentation and topic caption text extraction, as well as content based video browsing and querying, are addressed in detail.
本文详细讲述了新闻故事的分段，主题字幕文本的提取和在此之上的基于内容的视频浏览和查询。
应用推荐