hmm... good question. I haven't found any information for FaceNet that we use. Do you have similar information for any other face recognition system? I would like to see how they calculate it.
If I was EU citizen I would definitely sign this petition!
This sphere should be regulated properly. Face recognition is already in use in almost all EU countries. And who can afford it now? Only government and big companies have money to use it. Do they want to regulate themselves? Don’t think so.
CompreFace is free and, at least for now, I think it will be used only by enthusiasts. Then if face recognition became popular among small companies, the government would like to regulate it.
Another point - CompreFace stores the data only in the local storage. Unlike any SaaS solution, the government can’t just ask CompreFace to share the data, we just don’t have it. And, the thing I forgot to mention, there is a mode in which CompreFace doesn’t store photos!
And last, but not least, I understand that when face recognition is used on a huge scale, it could lead to very unpleasant consequences. E.g. in the worst scenario, if a face recognition system in the airport thinks you are a criminal - you can miss your flight and your vacation will be ruined.
But what if small businesses use face recognition? E.g. if your local gym adds face recognition and when you enter the building, the person on check-in says to you “Hey Mr. X, welcome back, your personal trainer is waiting for you”, and the trainer has already received a notification that you are here. The worst scenario - the person on check-in says not your name. And the best thing that we will be able to learn from these mistakes, and the mistakes won’t be so painful.
Disclaimer, this is my own opinion and may not coincide with the official opinion of the company.
I looked at other custom components, and it looks like it's not so difficult to add this integration.
But it would be better if someone from home-assistant community create it, as they already know how to run and test the system. We will be happy to help them in this case.
I'll still add it to our backlog, I believe IoT is very promising direction for CompreFace, so I would like to support such things in the future.
I just remembered, there is no face recognition in google cloud, they provide only face detection.
If you need face detection, you still can use CompreFace, just don't upload any photos to Face Collection, and it will just find the face and return it's coordinates
You need to host it on your servers, so you still need pay for the servers, or at least for electricity if they in your home/office :)
CompreFace is free, there is no paid version
Yes, we will publish docker-compose configs that uses insightface with some of the nearest releases.
We'll still support Facenet as well, so we'll see what library is more popular.
We are going to add landmarks information in one of the next releases. I think It could be calculated from this data. But I understand that it's better to add such functionality to CompreFace, I'll add this to our backlog
Wow, I hope CompreFace will suit you.
Feel free to contact me here, or in any other way(gitter, issues in github, support email) if you have any issues.
We are really trying to make it easy to install and use, but I need to be sure that we succeeded :)
Hi thatwasunusual, I'm happy that I read your comment after your edit, no hard feelings ;)
Just to clarify, all data is stored locally.
It could be run even without internet, once it's downloaded from dockerhub
I have one question to you as for the person who definitely concerned about privacy
To better understand what features are popular we are planning to gather anonymous information from the next release.
What measures we are going to take:
1. You will be asked for permit during the first registration. If no permit - we won't send anything
2. We send only anonymized information - no names, no geolocation data, no images, etc.
3. We are open source, so it's easy to check if we send only this information, all code is in github.
Hey everyone, we are creating a CompreFace - face recognition solution for developers that could be used without a machine learning experience.
It can be used as any paid SaaS like Amazon Rekognition, but it’s totally free.
How to use it:
1. Start the service with one command using docker-compose config
2. Use UI to create face collections
3. Use REST API to add faces to face collections and recognize faces
We also have a roles system, so you can control who has access to face collections.
We use the FaceNet library under the hood, but we are planning to add support of the InsightFace library.
What we are planning to add in the next release:
* Support of face detection and face verification (only face identification for now)
* GPU support
* Support of age and gender detection
We really need your feedback:
* Does it make sense for you to use ready-to-use solutions instead of python libraries?
* What more features do you expect from such a solution?
* It would be great if you try to install it - we tried our best to make it as simple as possible, we want to check it on a wide audience