Masked face recognition using frontal and profile faces with multiple fusion levels

Alqaralleh, Esraa; Afaneh, Ayman; Toygar, Önsen

doi:10.1007/s11760-022-02345-6

Cited by 5 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, our approach dynamically fuses multi-modal information using modality prediction probability, making full use of the complementary information provided by each modality. The proposed offers several advantages: (1) We proposed an adaptive face anti-spoofing approach that prioritizes the sensitive information in both real and fake images, while minimizing the impact of irrelevant information that could mislead classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Face Anti-Spoofing Approach Driven by Multi-modal Confidence Constraint and Adaptive Feature Weighting

Sun

Huang

Tian

et al. 2023

Preprint

View full text Add to dashboard Cite

Directly combining multi-modal features can result in overlooking the complementary information between different modalities and disregarding their interaction, given above, this paper proposes an approach for face anti-spoofing driven by the multi-modal confidence constraints and adaptive feature weighting. The first step is to utilize a multi-modal confidence constraint (MCC) loss, which helps to better regulate the fusion features and prevent overfitting. The MCC loss contributes to the loss of each mode and applies modulation constraints to enhance the accuracy of prediction probabilities. To fully utilize the discrimi-nant information and reduce interference factors, an adaptation feature weighting (AFW) strategy is further employed to dynamically assign the prediction probabilities between modalities. Finally, the fused features are classified using a binary cross-entropy loss function. To wrap up, the paper conducts qualitative and quantitative experiments on two public datasets: CASIA-SURF and CASIA-SURF CeFA. The results show that the approach is effective, achieving average error rates of 0.068% and 2.160% on CASIA-SURF and CASIA-SURF CeFA, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Face recognition technology [1] is highly convenient and accurate, making it a popular choice for interactive intelligent applications like sign-in and mobile payment. However, in recent years, face biometric recognition systems have become vulnerable to various spoofing attacks, including printing, replay, makeup, and 3D attacks [2][3].…”

Section: Introductionmentioning

confidence: 99%