How to do face recognition and comparison on DeepStream6.0?

I was able to identify the faces in the video and where they were using some inference engines,I want to further extract the eigenvalue of the face and compare it with the existing facial diagnostic information,how can I achieve this effect?Or if there are examples?

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Hello,kayccc
My complete information:
**• Hardware Platform ->Jetson NX
**• DeepStream Version->DeepStream6.0
**• JetPack Version ->4.6
**• TensorRT Version->8.0.1.6
**• Issue Type-> new requirements
**• Requirement details:I want to do face recognition and comparison on infer pipeline.

Hi,

In general, you will need an extra classifier (face recognition) to get the face feature.
This classification model can be used as a secondary inference engine.

Once you mark the feature layer as output, you can get the tensor value in a similar way as below sample:

/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-image-meta-test

So you can apply the comparison (ex. the distance between features) based on your requirement.
Thanks.

1 Like