Train Media Server to Recognize Faces

To run face recognition you must train Media Server by providing images of people that you want to identify. When you run face recognition, Media Server compares the faces it detects in the image or video to the faces that you added during training.

The following diagram shows how Media Server stores information you provide during training.

The "Media Server database" can represent either the internal Media Server database or a database on an external database server. For information on setting up this database, see Introduction.

You can organize faces into databases. These face databases are for organizational purposes. For example, you might have a database for politicians, a database for actors and a database for musicians. If you want to recognize only actors, you can then run face recognition using only that database.

A database can contain any number of faces, each representing a single person. Each face has an identifier, which must be unique. You can associate metadata with a face, for example the person's name or other information.

To each face you must add one or more training images. HPE recommends adding multiple training images for best performance. For information about choosing suitable training images, see Select Images for Training.