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

What does face_image_demo_eyes.m do? #13

Closed
hki541 opened this issue Jun 7, 2016 · 2 comments
Closed

What does face_image_demo_eyes.m do? #13

hki541 opened this issue Jun 7, 2016 · 2 comments

Comments

@hki541
Copy link

hki541 commented Jun 7, 2016

Hi
I just downloaded whole file on github (https://github.com/TadasBaltrusaitis/OpenFace) and found that there is a file which is not mentioned in readme.
(located in matlab_version\demo\face_image_demo_eyes.m)

I found that in this file at line 19, the first parameter of function Load_Patch_Experts() which should be the file direction is point to the author's c drive and I can not find the file name “svr_patches_*_synth.mat” in the whole open face folder.Therefore I can not run this file.

I would like to know that if this file can label landmark only on eyes without the whole face. If so, would you release the new version of the code? If not, what would this code do?

Thanks.

@TadasBaltrusaitis
Copy link
Owner

Hi,

It is left over from a slightly older version of the code. The functionality for this has been moved to the C++ version of the code, what it was supposed to do is track eyes once the facial landmarks have been detected (that is what the hierarchical C++ model does).

For using that model you would still need to have access to facial landmark detection (so the whole face would have to be visible). Unless you use an external eye detector.

I will try finding the .mat file for the eye model if I still have it.

Thanks,
Tadas

@TadasBaltrusaitis
Copy link
Owner

The newest version of the code can now track more precise eye landmarks in a demo script.

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