复杂色彩单帧图像中的文字提取

Single frame characters extraction in complex chromatic image

本文依据图像中文字与其背景存在的色彩差异,提出从复杂色彩单帧图像中提取文字的新算法.对彩色图像在HSV颜色空间进行色彩聚类形成颜色图层,再通过投影算法将颜色图层进一步细分为子图层进行图层分析,最后通过子图层合并产生备选文字图层.实验结果表明,本算法能够良好地从各种复杂颜色背景中提取垂直或平行于图像边缘的单色文字.

This paper proposes a new algorithm of character extraction in complex chromatic image based on color difference between the characters and the background. The color layer is firstly clustered in HSV color space from the chromatic image. Then the sub layers are divided through the projection algorithm from the color layers. Further, whether the sub layers contain characters are analyzed. After combining the sub layers which contain the characters, the character layers are finally emerged. The experimental results show that the proposed algorithm has the ability to extract characters in the complex chromatic image.