Existing datasets
CAISA-MFSD[2012]
- Easy-API[link]
SiW[2018]
- dataset-download-link[passdoor]【磁盤空間約210G！！！】.
- paper : Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision[CVPR-2018].
- num_subj = 165【8-live + 20-spoof for each subjec】,total 165 * 28 = 4620 videos.
- 4 sessions:
- 改變subject-face與camera的距離；
- 改變subject-face與camera的yaw-angle，範圍[-90, 90];
- 1 + 點光源的打光方向；
- 2 + 點光源的打光方向；
- dataset-glimpse
