微型电脑应用

图像和视频中包含着丰富的文本信息,提取和识别图像文本信息非常具有实际意义。传统的图像文本信息提取方法大多基于字符的代数和几何特征。作者从另一个角度出发,将彩色字符看成彩色图像的一部分,使类似字符的景物也可以被当作字符识别出来。文中提出一种基于Mean-Shift算法的图像文本信息提取方法,首先利用Mean-Shift算法对图像进行分割,然后对分割得到的文本区域进行投影分析从而将每个字符分割出来,最后将字符识别。

Text present in images and video contains useful information for automatic annotation Extraction of this information makes sense in research and application.The classical methods are mainly based on statistics or geometry.In this paper,the text in the images is taken as a kind of scenery not the characters.Follow this way,some semantics which constituted by scenery are taken as a kind of text The adopted algorithm to complete the intention is the Mean-Shift algorithm which is used to detect text.After detection,the characters are extracted from the text by projection segment