Skip to content

A simple face anti-spoofing based on CNN trained with HSV + YCrCb color feature, implemented with tensorflow and keras.

Notifications You must be signed in to change notification settings

Oreobird/Face-Anti-Spoofing

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Face-Anti-Spoofing

A simple face anti-spoofing based on CNN trained with HSV + YCrCb color feature.

Network Architecture

Dependencies:

	dlib >= 19.17.0
	tensorflow >= 1.12.0
	keras >= 2.2.4
	numpy >= 1.11.1
	scipy >= 0.14
	opencv-python >= 3.4.3

Usage:

  • Data prepare:
    1) Download train data and model file from:
    https://pan.baidu.com/s/1izOKKs8-CRy6Ykfa13r0Ew code: u99k
    2) untar data and model to your project dir
  • Train model:
    python data/NUAA/gen_label.py python main.py --train=True
  • Test online via camera:
    python main.py --online=True

Detailed design doc, please reference to:

image

About

A simple face anti-spoofing based on CNN trained with HSV + YCrCb color feature, implemented with tensorflow and keras.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages