Improving Face Anti-Spoofing by 3D Virtual Synthesis

2 Jan 2019Jianzhu GuoXiangyu ZhuJinchuan XiaoZhen LeiGenxun WanStan Z. Li

Face anti-spoofing is crucial for the security of face recognition systems. Learning based methods especially deep learning based methods need large-scale training samples to reduce overfitting... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Face Anti-Spoofing CASIA-MFSD 3D Synthesis (balancing sampling) EER 2.22 # 2
HTER 1.67 # 1
Face Anti-Spoofing Replay-Attack 3D Synthesis (balancing sampling) EER 0.25 # 3
HTER 0.63 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet