摘要
视频文字信息在基于语义的视频分析、检索、提取中占有重要地位。根据视频中文字和背景的灰度变化程度不同,提出一种基于梯度离散余弦变换的视频文字定位方法:先对视频帧进行N×N分块,计算每一块的离散余弦变换系数,然后求出梯度算子的幅值,利用得到的幅值作为块强度进行平滑滤波以及形态学处理,最后对图像进行水平和垂直方向投影,统计字幕条数,并利用文本框标识文字区域,进而达到对视频文字定位的目的。仿真结果表明这种视频文字定位方法对于静态文字和滚动字幕的定位均是可行的,且其算法的运行速度快、效率高,特别是对于笔画较少的文字定位准确,不会出现遗漏现象。
Video text information plays an important role in semantic-based video analysis,indexing and retrieval.The grade of gray in the video text and background is different,so an approach to video text localization using gradient discrete cosines transform（DCT） was proposed.Firstly,the video frame is divided into N×N macro-blocks,and we can get the DCT coefficients from every macro-block.Then the gradient operator value considered as block intensity is calculated and we deal with it by using of smooth filter and morphology processing.Lastly,the horizontal and vertical projection can be obtained,the number of text line can be got and the text region is marked with text box.The experimental results show that the proposed method is efficient on the localization of the static and rolling video text,especially the accuracy and integrality of character localization with the less strokes.
出处
《计算机科学》
CSCD
北大核心
2011年第9期271-274,293,共5页
Computer Science
基金
中国博士后科学基金(20090450750)资助
关键词
文字定位
视频帧
梯度
Text localization
Video frame
Gradient
