Recognize Faces

This section describes how to create an analysis task to recognize faces that appear in media.

TIP: To run face recognition, you must first detect faces by setting up a face detection task. For information about how to do this, see Detect Faces.

To recognize faces in media

  1. Create a new configuration to send to Media Server with the process action, or open an existing configuration that you want to modify.

  2. In the [Session] section, add a new analysis task by setting the EngineN parameter. You can give the task any name, for example:

    [Session]
    Engine0=Ingest
    Engine1=FaceDetect
    Engine2=FaceRecognize
  3. Create a new configuration section to contain the task settings, and set the following parameters:

    Type The analysis engine to use. Set this parameter to FaceRecognize.
    Input The track that contains detected faces that you want to recognize. Providing you have sufficient computational resources, OpenText recommends setting this parameter to the DataWithSource output track from your face detection task. For example, if your face detection task is named FaceDetect, set this parameter to FaceDetect.DataWithSource. Alternatively, you can use the ResultWithSource track produced by your face detection task.
    Database (Optional) A comma-separated list of face databases to use for recognition. By default, Media Server uses all available data. Database names are case-sensitive.
    MaxFaces The total number of faces that you want to recognize. For example if there are 600 faces in your face database, set MaxFaces=600. The value of this parameter determines how many channels are required to run the face recognition task.
    RecognitionThreshold (Optional) The minimum confidence score required to recognize a face.
    MaxRecognitionResults (Optional) The maximum number of results to return, if the face matches more than one entry in the training database(s).

    For example:

    [FaceRecognize]
    Type=FaceRecognize
    Input=FaceDetect.DataWithSource
    RecognitionThreshold=60
    MaxRecognitionResults=1
    

    For a complete list of parameters that you can use to configure a face recognition task, and more information about these parameters, refer to the Media Server Reference.

  4. Save and close the configuration file. OpenText recommends that you save your configuration files in the location specified by the ConfigDirectory parameter.