Face Recognition

Face Recognition identifies faces that are detected in media. Before using face recognition you must train Media Server to recognize faces, by providing images of people who you want to recognize.

Configuration Parameter Description
Database A face database to use to recognize faces. Media Server compares the detected faces to faces in this database.
DisableFineTuning Specifies whether to ignore the optimized neural network (if you generated one using the FinetuneFaceDatabase action) and instead use the standard network.
GPUBatchingDuration The maximum amount of time to wait, before sending a batch of video frames to the GPU for analysis.
GPUNumParallel The maximum number of video frames to analyze concurrently using the GPU (per CPU thread).
Identifier A comma-separated list of identifiers that specifies the faces to recognize.
Input The track that you want to analyze.
MaxFaces The maximum number of faces that you want to recognize.
MaxRecognitionResults The maximum number of recognition results to return per face.
Metadata A metadata field name and value that specifies the faces to recognize.
NumParallel The maximum number of CPU threads to use for analysis.
OutputIdentities The types of identities to include in the output (all, known, or unknown).
RecognitionThreshold The minimum confidence score required to consider a face as a match.
SegmentDuration The maximum duration of a record in the SegmentedResult or SegmentedResultWithSource track.
SyncDatabase Specifies whether to synchronize with the training database before beginning the analysis task.
Type The analysis engine to use. Set this parameter to FaceRecognize.

Output Tracks

Output track Description Output1
Data Contains records that describe a face recognition result for a single input record. No
DataWithSource

The same as the Data track, but each record also includes the source frame.

No
Result Contains zero or more records, each describing a face recognition result, for each detected face. (There can be multiple recognition results when there are several matches that exceed the recognition threshold. See the configuration parameters OutputIdentities, RecognitionThreshold, and MaxRecognitionResults). Face recognition results inherit their ID from the detected face, so all of the recognition results for the same detected face have the same ID. Yes
ResultWithSource

The same as the Result track, but each record also includes the best source frame.

No
SegmentedResult

(Available only when processing video). The same as the Result track, except the duration of each record is limited by the parameter SegmentDuration. If a result exceeds the specified duration, Media Server begins a new record with the same ID.

Yes
SegmentedResultWithSource

(Available only when processing video). The same as the ResultWithSource track, except the duration of each record is limited by the parameter SegmentDuration. If a result exceeds the specified duration, Media Server begins a new record with the same ID.

No

For more information see Face Recognition Results or use the action GetExampleRecord.