[On-Premise] Face comparison on premise?

Question

Hi,

I'm currently learning on AWS Rekognition. I am quite interested in the AWS Rekognition SDK, especially the Face Comparison. Is there any diagram flow regarding this service? From what I understand, the Face Comparison is done on the cloud because when doing the comparison I need to upload the image.

Is the image that I upload saved on temp storage or not? And is it possible to do it without uploading the image so all the process is done on-premise?

Thank you

Answer

Hello, with [search_faces_by_image](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/rekognition.html#Rekognition.Client.search_faces_by_image) API you can send Blob of image bytes up to 5 MBs.  
The image needs to be saved in a temporary storage because Rekognition turns it into a vector to search a similar face in the Collection.

You can't use Rekognition on premise. Alternatively, you can use [AWS Panorama](https://aws.amazon.com/panorama/), which is an appliance and software development kit (SDK) that brings CV to on-premises internet protocol (IP) cameras.

[On-Premise] Face comparison on premise?

Relevant content