Face database generation based on text–video correlation

• A face database generation framework based on text–video correlation is proposed.
• The system is able to reduce 90% of the human effort in face database construction.
• We utilize scripts and subtitles of videos to remove face recognition errors.
• We introduce timing projection method for text and video correlation.

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.