face-landmark-localization

This is a project predict face landmarks (68 points) and head pose (3d pose, yaw,roll,pitch).

Install

• caffe
• dlib face detector

  you can down dlib18.17

  cd your dlib folder

  cd python_example

  ./compile_dlib_python_module.bat

  add dlib.so to the python path

  if using dlib18.18, you can follow the official instruction

• opencv

Usage for images

• Command : python landmarkPredict.py predictImage testList.txt

  (testList.txt is a file contain the path of the images.)

Usage for usb camera

This sctpt enables you to see intractive results for this face-landmark-localization.

usage: landmarkPredict_video.py uvcID

• Command : python landmarkPredict_video.py 0

Model

• You can download the pre-trained model from here

Train

• add train.prototxt and train_solver.prototxt files, Training using the 300W data set

Result

---

class based rewrite for the landmarkPredict.

facePos.py: FacePosePredictor class is defined.

librect.py: helper functions for rectangles.

landmarkPredict_video.py uses this class version.