Face database generation based on text-video correlation
Face database generation based on text-video correlation
复制标题
DOI：
10.1016/j.neucom.2016.05.009
复制
发表时间：
2016-09
期刊：
影响因子：
6
通讯作者：
Dan Zeng;Yixin Bao;Ke Liu;Fan Zhao;Q. Tian
中科院分区：
文献类型：
--
作者：
Dan Zeng;Yixin Bao;Ke Liu;Fan Zhao;Q. Tian
数据库的大小是人脸识别系统成功的关键。然而，建立这样的数据库既耗时又费力。在本文中，我们解决这个问题，提出了一个数据库生成框架的基础上，文本视频相关性。具体而言，视频的视觉内容可以通过人脸检测、跟踪和识别呈现为字符序列，而从字幕和脚本中提取的文本信息提供互补的身份序列。通过将这两个序列相关联，可以在没有人工干预的情况下改进识别的面部。实验结果表明，该方法可以减少90%的人脸数据库构建工作量。
The size of databases is the key to success to face recognition systems. However, building such a database is both time-consuming and labor intensive. In this paper, we address the problem by proposing a database generation framework based on text–video correlation. Specifically, visual content of a video can be presented as a character sequence by face detection, tracking and recognition, while text information extracted from subtitles and scripts provides complementary identity sequence. By correlating these two sequences, faces recognized can be refined without manual intervention. Experiments demonstrate that 90% of the human effort in face database construction can be reduced.