Janspiry / face-mask-segmentation

【Tools】Face recognition and attribute segmentation using Python, dlib, and One Millisecond Face Alignment with an Ensemble of Regression Trees](http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Kazemi_One_Millisecond_Face_2014_CVPR_paper.pdf).

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Face Mask Segmentation

Face recognition and attribute segmentation using Python, dlib, and One Millisecond Face Alignment with an Ensemble of Regression Trees.

The dlib installation in windows platform you can infer my blog:

Examples

Command:

python project.py

Data:

image-20201209220210034

Output:

I extract the nose,eyes attributes mask

image-20201209215918743

Method

First We selected some pictures from CelebA-HQ,and use dlib to recognition and location some our wanted attributes.

Take nose as a example, choose 29-36 as my index referring to the picture below, then compute their midpoint. In the last, intercept the mask by midpoint and our patch_size(output size).

image-20201209220524489

About

【Tools】Face recognition and attribute segmentation using Python, dlib, and One Millisecond Face Alignment with an Ensemble of Regression Trees](http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Kazemi_One_Millisecond_Face_2014_CVPR_paper.pdf).


Languages

Language:Python 100.0%