基于颜色和边缘特征的新闻视频标题条检测  

Caption Detection and Recognition in News Video Based on Color and Edge Features

作　　者：杨哲[1] 史萍[1] 

机构地区：[1]中国传媒大学信息工程学院,北京100024

出　　处：《电视技术》2012年第19期163-166,共4页Video Engineering

基　　金：北京市重点学科建设项目

摘　　要：提出了一种基于颜色和边缘特征的新闻视频标题条检测和文字识别方法。该方法首先利用颜色和边缘特征检测出新闻视频中含有标题条的帧,然后由先验知识得出标题条帧中的字幕区域,对字幕区域进行预处理和光学字符识别(OCR),得到文字内容。实验结果表明该方法具有较高的查全率和查准率。A new method to detect and recognize news captions in news video based on color and edge features is proposed in this paper. First, the color and edge features are used to detect caption frames in news video. Then, the caption areas are determined by some priori knowledge. Finally, texts in caption areas are obtained after pre-processions and OCR recognition. Experimental results show that the method has a better performance in recall rate and precision rate.

关 键 词：新闻视频 标题条 颜色特征 边缘特征 OCR 

分 类 号：TN919.8[电子电信—通信与信息系统]