Analysis

The [Analysis] section of the configuration lists the analysis tasks that you want to run. A configuration can contain any number of analysis tasks. For example, you can run face detection and object recognition at the same time.

The following example includes a single analysis task named OCRtext. The task uses the OCR analysis engine:

[Analysis]
AnalysisEngine0=OCRtext

[OCRtext]
Type=ocr
Input=Image_1

An analysis engine accepts input of a particular type. For example, the OCR engine requires an image track, and the SpeakerID engine requires an audio track. The analysis engine only processes records from the track specified by the Input configuration parameter. In this example, the OCR engine processes the Image_1 track produced by the ingest engine. If you do not specify an input track, the engine uses the first track of the required type produced by the ingest engine. The engine would automatically attempt to process the Image_1 track.

To find out what type of input is required by an analysis engine, send action=getstatus to HPE Media Server. The response includes information about the input and output tracks for the analysis engines.

The input could be an output track from another engine, provided the track type is compatible. In the following example, the input of the face recognition task is the ResultWithSource output track of the face detection task:

[Analysis]
AnalysisEngine0=FaceDetect
AnalysisEngine1=FaceRecognize

[FaceDetect]
Type=FaceDetect
...

[FaceRecognize]
Type=FaceRecognize
Input=FaceDetect.ResultWithSource
...

To be used as the input for a task, a track must provide at least the required record types. For information about the output tracks produced by HPE Media Server engines, use action=getstatus or refer to the HPE Media Server Reference.


_HP_HTML5_bannerTitle.htm