face dataset

>> python ict_download.py

download it to project directory shape_predictor_68_face_landmarks.dat file

make image meta file.

run

python pyqt.py

and then open meta file directory.

now you can edit landmark detection.

image

60 images

15 neutral pose num : 1 - 0 degree pose num : 6 - yaw -90 ~ 90 (per 30 degree) : this mean left and right head num : 4 - pitch-30 ~ 30 (per 15 degree) num : 4 - roll -30 ~ 30 (per 15 degree)

non-rigid pose(expression) 3 yaw angle -30, 0, 30 mouth stretch

1. smile
2. brow raise
3. disgust
4. squeeze left eye
5. squeeze right eye
6. anger
7. jaw left
8. jaw right
9. grin
10. chin raise
11. lip pucker
12. lip funnel
13. cheek blowing
14. eyes closed

predeifned_weight

[basis_w, expr_1_w expr_2_w .... expr_n_w ]