Live visualisation of various facial recognition algorithms.
Go to file
Ruben van de Ven b3a0e4035b Exe build command documented 2020-10-12 15:59:25 +02:00
.vscode latest visualhaar 2020-10-02 14:11:02 +02:00
dnn All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
face_recognition Windows pyinstaller compatibilities 2020-10-12 15:27:43 +02:00
visualhaar@a6ac50c3b3 update visualhaar 2020-10-02 14:59:54 +02:00
.gitignore Save images with spacebar 2020-09-23 17:18:10 +02:00
.gitmodules Crisper output and many configuration to cli arguments 2020-09-23 15:58:36 +02:00
README.md Exe build command documented 2020-10-12 15:59:25 +02:00
build_exe.bat Exe build command documented 2020-10-12 15:59:25 +02:00
dnn_test.py All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
haarcascade_frontalface_alt2.xml All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
hog_test.py All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
live_dnn.py All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
live_hog.py All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
mirror.py Windows pyinstaller compatibilities 2020-10-12 15:27:43 +02:00
recognition_test.py All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
requirements.txt changes for windows compatibility 2020-09-24 10:06:28 +02:00
test_rec.py All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
test_rust.py Crisper output and many configuration to cli arguments 2020-09-23 15:58:36 +02:00
video_multiprocess.py All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00
video_threading.py All sorts of test scripts and the first functional mirror version 2020-09-15 10:28:52 +02:00

README.md

A mirror which shows which faces are detected through three different facial detection algorithms:

  • OpenCV's deep neural net 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
  • Install VS C++
  • Install Cmake (needed for python dlib)
    • make sure to add it to path
  • Install git
    • including ssh deploy key
  • git clone https://git.rubenvandeven.com/r/face_detector
  • cd face_recognition
  • pip install virtualenv
  • virtualenv.exe venv
  • .\venv\Scripts\activate
  • cd .\dnn\face_detector
  • python.exe .\download_weights.py
  • cd .\visualhaar
  • Either one of:
  • Make the installer:
    • build_exe.bat