Trains Media Server to recognize any faces that exist in its database and have incomplete or out-of-date training (any faces that have one or more images with a status of untrained). For example, you must re-train a face if you add new face images.

Type: asynchronous

Parameter Description Required
database The name of a database to process. Set this parameter to train Media Server to recognize faces in the specified database only. By default, this action trains Media Server to recognize faces in all databases. No
numparallel The maximum number of threads that the action can use (default 1). No




This action is asynchronous, so Media Server always returns success accompanied by a token:


You can use this token with the QueueInfo action to retrieve the status of the action:

        <queued_time>2015-Nov-30 16:52:51</queued_time>
        <process_start_time>2015-Nov-30 16:52:51</process_start_time>
        <process_end_time>2015-Nov-30 16:52:52</process_end_time>