5

Currently I don't know which library I should use

OpenFace OpenBR OpenCV

My system hast to recognize about 10 different persons and it will run on a Raspberry Pi 3 with the Raspberry Pi Camera Module v2. The light conditions will differ and it the system should work with and without glasses. Furthermore it has to recognize a person in less than 2 seconds.

I know that OpenFace uses a different approach on face recognition and the recognition accuracy is better. But will it work on a Raspberry Pi 3 or will it be to slow?

What are the differences between OpenCV and OpenBR? Which one has better accuracy rates?

closed as too broad by Jacobm001 Feb 27 '17 at 22:08

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 2
    Sounds like you're the perfect candidate to put all three to the test :) – Ghanima Oct 11 '16 at 15:57
  • as your questions are specific to opencv, they should posted on answers.opencv.org or on the main stack over flow site as they have a better chance of getting answered there. any questions or problems specific (hw or sw related) to the RPi belong here. – Shreyas Murali Oct 11 '16 at 18:09
2

Here's the low down:

  • OpenFace is a python system, that will make it inherently slower than a compiled (C, C++) application (like OpenCV and OpenBR) of same computational weight.
  • OpenCV is for general computer vision applications
  • OpenBR is specifically for Biometric Recognition and uses OpenCV.

Basically, if speed is of the essence for your application, stay away from OpenFace. And unless you have better OpenCV abilities than the OpenBR team, you should stick to using the OpenBR solution. It has a port specifically for Raspbian too.

Not the answer you're looking for? Browse other questions tagged or ask your own question.