Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learn Convolutional Neural Network for Face Anti-Spoofing

About

Though having achieved some progresses, the hand-crafted texture features, e.g., LBP [23], LBP-TOP [11] are still unable to capture the most discriminative cues between genuine and fake faces. In this paper, instead of designing feature by ourselves, we rely on the deep convolutional neural network (CNN) to learn features of high discriminative ability in a supervised manner. Combined with some data pre-processing, the face anti-spoofing performance improves drastically. In the experiments, over 70% relative decrease of Half Total Error Rate (HTER) is achieved on two challenging datasets, CASIA [36] and REPLAY-ATTACK [7] compared with the state-of-the-art. Meanwhile, the experimental results from inter-tests between two datasets indicates CNN can obtain features with better generalization ability. Moreover, the nets trained using combined data from two datasets have less biases between two datasets.

Jianwei Yang, Zhen Lei, Stan Z. Li• 2014

Related benchmarks

TaskDatasetResultRank
Face Anti-SpoofingOULU-NPU ICM → O
HTER29.61
115
Face Anti-SpoofingIdiap Replay-Attack OCM → I
HTER34.47
96
Face Anti-SpoofingMSU-MFSD OCI → M
HTER29.25
85
Face Anti-SpoofingCASIA-MFSD O&M&I to C (test)
HTER34.88
28
Face Anti-SpoofingCASIA-FASD, Replay-Attack, and MSU-MFSD Cross-Database
HTER (Train CASIA / Test Replay)48.5
10
Showing 5 of 5 rows

Other info

Follow for update