Development of the Telop Retrieval System for Educational Video Data

基于字幕特征的视频字幕检索系统可以从海量的视频数据中检索出与查询对应的字幕。在此基础上，开发了一个基于字幕字符的字幕检索系统。该方法通过计算字幕字符的各图像特征与查询关键字的模板图像特征之间的距离来确定合适的字幕。使用91个查询关键词的实验结果表明，使用1-gram特征的方法的平均准确率为98。61%，使用2克特征变成99.百分之五十九此外，检索时间可以在约0。使用2克功能时为5秒

Video telop retrieval systems based on telop characters can retrieve the corresponding telops to the query from the huge video data. On this research, a new telop retrieval system based on telop characters is developed. In order to specify the suitable telop, this method calculates the distance between each image features of telop characters and template image features of query keyword. Experimental results, using 91 query keywords, show that the average precision of proposed method using 1-gram feature becomes 98. 61%, and using 2-gram feature becomes 99. 59%. Moreover, the retrieval time can be obtained in about 0. 5 seconds when using 2-gram feature