Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

more Facial landmark in mtcnn #62

Closed
SaddamBInSyed opened this issue Feb 19, 2020 · 4 comments
Closed

more Facial landmark in mtcnn #62

SaddamBInSyed opened this issue Feb 19, 2020 · 4 comments

Comments

@SaddamBInSyed
Copy link

@jkjung-avt ,
Thanks for your work.

how to get 68 points facial landmark (as like dlib) using MTCNN.
currently, it's giving only 5 facial points.
Since I want to do head pose estimation I am need of the other facial points

please advise.

@jkjung-avt
Copy link
Owner

MTCNN is designed and trained with only 5 facial landmarks. If you want to do 68 points, you need to train your own model.

Reference: official web site of MTCNN

image

@SaddamBInSyed
Copy link
Author

thanks for the information

@SaddamBInSyed
Copy link
Author

SaddamBInSyed commented Feb 20, 2020

@jkjung-avt ,

how to extract/crop left_eye and right_eye image from mtcnn facial landmark.
I want to find face drowsiness and other stuff.

your help highly appreciated.
thanks

@SaddamBInSyed SaddamBInSyed reopened this Feb 20, 2020
@jkjung-avt
Copy link
Owner

The landmarks output by MTCNN already include left and right eyes. I think you could use those to extract image crops of the eyes and maybe train a classifier to do drowsiness detection.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants