视频帧中字幕信息提取的区域检测算法研究

Research on Area-detecting Algorithm for Text Extraction from Video Frames

从影视字幕中获取相应的文本,可为影视节目的内容检索提供一种重要的手段。针对从视频数据中截取下来的帧数据,对灰度化后的彩色单帧视频中的字幕分割方法进行了探讨,提出了区域检测算法的处理方案,实验结果表明用该方法获取文本信息是合理有效的。

Text area extraction from video caption has become an important tool for content-based video retrieval. Test object is frame data intercepted from video data. Segmentation methods of caption text that embedded in the color single-frame video by grayed processing are discussed. In this paper, the algorithm of area detection is proposed to solve the above problems. Experimental results show that the proposed approach is very effective and reasonable in text area detection.