2020-10-01 16:22:15 +02:00
A `mirror` which shows which faces are detected through three different facial detection algorithms:
* OpenCV's deep neural net [face detector ](https://github.com/opencv/opencv/tree/master/samples/dnn/face_detector ).
* Dlib's default frontal face detector, which is HOG based
* A Viola-Jones Haarcascade detection. Any OpenCV compatible xml file should work. It defaults to the canonical `haarcascade_frontalface_alt2.xml` .
# Installation
## on windows
The installation in Windows can be done, though it is quite elaborate:
* Install python3
2020-12-21 12:04:38 +01:00
* Install VS C++ build tools
2020-10-01 16:22:15 +02:00
* Install Cmake (needed for python dlib)
+ make sure to add it to path
* Install git
+ including ssh deploy key
2020-12-21 12:04:38 +01:00
* `git clone https://git.rubenvandeven.com/r/face_recognition`
2020-10-01 16:22:15 +02:00
* `cd face_recognition`
* `pip install virtualenv`
* `virtualenv.exe venv`
2020-12-21 12:04:38 +01:00
+ Might be that you need to run: `C:\Users\DP Medialab\AppData\Roaming\Python\Python39\Scripts\virtualenv.exe` (see pip output)
2020-10-01 16:22:15 +02:00
* `.\venv\Scripts\activate`
2020-12-21 12:04:38 +01:00
+ Might be that you need to first run `Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser`
2020-10-01 16:22:15 +02:00
* `cd .\dnn\face_detector`
* `python.exe .\download_weights.py`
2020-12-21 12:04:38 +01:00
* `cd ..\..`
* `pip.exe install -r requirements.txt`
2020-10-01 16:22:15 +02:00
* `cd .\visualhaar`
2020-10-02 16:52:34 +02:00
* Either one of:
+ Compile rust library
* Install rustup-init
* `git submodules init`
* `git submodules update`
* `cargo build --lib --release`
+ Download dll from https://git.rubenvandeven.com/r/visualhaar/releases
2020-12-21 15:03:01 +01:00
+ Fetch `SourceSansPro-Regular.ttf` from the internet
2020-10-12 15:59:25 +02:00
+ Make the installer:
2020-12-21 15:03:01 +01:00
* Either one of:
* `& 'C:\Users\DP Medialab\AppData\Roaming\Python\Python38\Scripts\pyinstaller.exe' .\mirror.py --add-binary '.\visualhaar\target\release\visual_haarcascades_lib.dll;.' --add-data '.\haarcascade_frontalface_alt2.xml;.' --add-data '.\SourceSansPro-Regular.ttf;.' --add-data 'dnn;dnn'`
* `& '.\venv\Scripts\pyinstaller.exe' .\mirror.py --add-binary '.\visualhaar\target\release\visual_haarcascades_lib.dll;.' --add-data '.\haarcascade_frontalface_alt2.xml;.' --add-data '.\SourceSansPro-Regular.ttf;.' --add-data 'dnn;dnn'`
2020-10-12 16:23:27 +02:00
* `mv '.\dist\mirror\mpl-data' '.\dist\mirror\matplotlib\'`
2020-12-21 12:04:38 +01:00
* `Compress-Archive -LiteralPath .\dist\mirror -DestinationPath .\dist\mirror.zip`
+ We could also [use wine for cross compilation ](https://www.andreafortuna.org/2017/12/27/how-to-cross-compile-a-python-script-into-a-windows-executable-on-linux/ ) from Linux
- make sure wine is set to pose as Windows 10 (`winecfg`)
- `wine ~/Downloads/python-3.9.0-amd64.exe` (or whichever version you use)
- Install for all users
-
## Instructor help
If screen stays black: is the camera on?
Enable camera through keyboard (MSI laptops: fn+F6). Then go to Settings/Instellingen -> Privacy instellingen voor camera -> Grant apps access to camera.
