Closed zhenglaizhang closed 6 years ago
Face alignment is not the main topic of our current work. We just follow the same pipeline of sphereface: to use 5 landmarks and then do similarity transform. The only difference is we use 112x112 instead of 112x96.
If your original face image is quite tight, black corners are likely to be happened.
We may provide a 3D-alignment library later, which will be much more accurate.
@nttstar great, thanks for the detailed info!
Some questions need you guys to help answer, thanks in advance!
add fixed margin 44
.similarity transformation
,face_preprocess.py
there are some commented code which looks like projective transform.test.py
, I use the mtcnn crop the testing images, without resizing and fixed 44 margin. I am not sure if this is by design or I am wrong with the cropping steps -:)mtcnn 5 landmarks