SoftwareGift / FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019

Code for 3rd Place Solution in Face Anti-spoofing Attack Detection Challenge @ CVPR2019,model only 0.35M!!! 1.88ms(CPU)
Other
928 stars 282 forks source link

Data Preprocessing Code #46

Open ybloch opened 5 years ago

ybloch commented 5 years ago

Could you please attach the code of the Data Preprocessing, I want to test the model with my own pictures ...

SoftwareGift commented 5 years ago

PRNet is used in Data Preprocess,and it takes a long time. I suggest you take a simpler way to remove the background。For example, you can get the depth of the background by taking the average depth of multiple points on the depth map as the depth of the face plane. The mask is filtered by the depth of the background, and the background information of RGB and IR is further removed.

ybloch commented 5 years ago

If the goal is just to get rid of the background then why not just use face segmentation on regular RGB images?