Efficient Face Spoofing Detection With Flash

Ebihara, Akinori F.; Sakurai, K.; Imaoka, Hitoshi

doi:10.1109/tbiom.2021.3076816

Cited by 6 publications

(1 citation statement)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motivated by the observation that spoofing face images contain intrinsic defects, some methods construct face PAD models with the help of noise [67] and spoofing traces modeling [68,69]. Similar to conventional methods, there are also some deep learning based face PAD designed from the perspective of intrinsic image decomposition [70,71] and reflection analysis [72]. Zhang et al [6] propose a method based on ResNet18 [97] with squeeze-andexcitation fusion (SEF) [98] to detect printed photo attacks in multi-modality scenarios.…”

Section: Auxiliary Tasksmentioning

confidence: 99%

Cross-domain face presentation attack detection techniques with attention to genuine faces

Li¹

View full text Add to dashboard Cite

PAD with the help of target domain data. However, it has always been a non-trivial challenge to collect sufficient data samples in the target domain, especially for attack samples. In the third work, we improve the cross-domain performance of the face PAD by only using a few genuine face samples collected in the target domain.We propose a method by introducing teacher-student learning to address the oneclass domain adaptation problem in face PAD. The similarity score between the representations of the teacher and student networks is used to distinguish attacks from genuine ones.To verify the effectiveness of the proposed methods, we devise protocols and conduct extensive experiments on multiple datasets. The experimental results show that our methods outperform prior methods.

show abstract