Does the face recognition model respect privacy?

27 Jul 2021, 11:17 p.m.

No personal data (images, metadata or AI learnings) ever leaves your local server if your run your own instance of Photonix.

We were able to develop face recognition without sending any data to the cloud and break it down so the only part that needs retraining specifically to your collection of faces is very fast. You can read the in-depth steps of our face detection and recognition model here if you are so inclined.

All the computationally intensive steps mentioned in that document are performed by pre-trained, industry-standard models. This gets us to the point where we have a fingerprint (or embedding) array of 128 numbers to roughly represent each detected face.

The very last step labelled Similarity Calculation / Clustering / Classification is the only part of the model that is built on the local machine. This similarity index is very quick to build (typically a few seconds) and just means that we don't have to compare the current face embedding individually with every other face embedding already in the system when we want to find the closest match.

Please sign up to the mailing list so we can notify you of our version 1.0 release and other important news. We will not pass your details on to any other party and you can unsubscribe at any time.



Feb 2021

Nice job, looks very good! Also I like the tags instead of albums feature!



Sep 2020

Looks like your app is on the right track!

Any chance for an ARM64 version?


May 2020

I love this project! My dream would be a photo organizer / tagger that just goes through all photos at night and automatically detects and learns the contents.... I will follow you for this project and am happy to test any versions.