摘要
视频数据中的文本能提供重要的语义信息。本文提出了一种视频文本自动定位、跟踪和识别的方法,首先用基于小波和LH检测视频帧文本所在的位置,然后用运动估计的方法,跟踪后继帧文本的位置,再用多帧平均的方法增强文本区域,最后经过二值化处理和连通分量分析,将文本字符送入OCR软件进行识别。实验结果表明,该方法简单易行,能快速地定位和跟踪文本区域,定位精度和识别效果良好。
Text in video can provide an important supplemental source of index semantic information. In this paper, an algorithm of automatic video text locating, tracking and recognition is presented. First, the text regions are located by several steps: wavelet decomposition, high frequency component intensity and density detection, horizontal and vertical convex detection based LH, and text locating. Then the text regions are tracked in next consecutive frames. After multiple frames averaging, the text regions are enhanced. By binarization of the enhanced text regions followed by component analysis, the text regions with clean background are obtained. Then the text regions are recognized by OCR software, the final text strings are attained. Experimental results show that the proposed algorithm can detect and track text region simply and effectively.
出处
《中国图象图形学报（A辑）》
CSCD
北大核心
2005年第4期457-462,i003,共7页
Journal of Image and Graphics
基金
国家自然科学基金项目(60372068)
广东省科学基金项目(011628)
