Oreobird / Face-Anti-Spoofing

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

Face-Anti-Spoofing

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

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: