Facial Recognition Query

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU): GPU
• DeepStream Version: 6.1

I would like to develop a FR app that would take RTSP stream as input. As per tao git repo deepstream_tao_apps/apps/tao_others/deepstream-faciallandmark-app at master · NVIDIA-AI-IOT/deepstream_tao_apps · GitHub they are predicting the facial landmarks position(please correct me if I’m wrong). How to calculate the distance with the existing database of pictures that I have, I mean how can I perform the recognition part?
Like Facenet is performing the detection part and FPENet is used for landmark estimation. How to match this landmark estimation with database? Moreover how to create this database? I’m completely lost. Or is there any other way.
Any help is highly appreciated.

@fanzh and all

Due to legal issues, there is no face recognition sample in DeepStream.

like Mainak Sen reacted to your message:

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.