The network detects 18 different (farther than 0.99) me when moving my head.

[educob]

Hi.

I have developed a little app that when detecting a face tries to find it in the database and if it's not there, it created a new record.
As I move my head the app thinks it's a new user (distance >= 0.99) and creates a new entry in the database.
Up to 18 records have been created.

I was thinking of developing a professional app for controlling access to places, etc.
How can I do to filter (or any other way) these extra records created with different head poses?

Thanks.

[justein]

@educob have you retrained the model？

[educob]

No. ZhaoJ9014 told in other issue days ago that I didn't need to train it.

I have used this trained model: backbone_ir50_ms1m_epoch120.pth

Today a friend told me that in order for him to enter his face in his iphone for facial recognition he has to move his head a lot (the phone even tells him things like: move more to the left).
So I guess I need some algorithm to how this works so the same person is not being taken for a new person.