arrow
返回

Asymmetric Modality Translation for Face Presentation Attack Detection

delete2023-01-01
delete10
delete
OA
AI
Z
Zhi Li
H
Haoliang Li *
X
Xin Luo
Y
Yongjian Hu
K
Kwok‐Yan Lam
A
Alex C. Kot
DOI:10.1109/TMM.2021.3121140delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Face presentation attack detection (PAD) is an essentialmeasure to protect face recognition systems from being spoofed by malicious users and has attracted great attention from both academia and industry. Although most of the existing methods can achieve desired performance to some extent, the generalization issue of face presentation attack detection under cross-domain settings (e.g., the setting of unseen attacks and varying illumination) remains to be solved. In this paper, we propose a novel framework based on asymmetric modality translation for face presentation attack detection in bi-modality scenarios. Under the framework, we establish connections between two modality images of genuine faces. Specifically, a novel modality fusion scheme is presented that the image of one modality is translated to the other one through an asymmetric modality translator, then fused with its corresponding paired image. The fusion result is fed as the input to a discriminator for inference. The training of the translator is supervised by an asymmetric modality translation loss. Besides, an illumination normalization module based on Pattern of Local Gravitational Force (PLGF) representation is used to reduce the impact of illumination variation. We conduct extensive experiments on three public datasets, which validate that our method is effective in detecting various types of attacks and achieves state-of-the-art performance under different evaluation protocols.
Keyword:
Face presentation attack detection
asymmetric modality translation
modality fusion
unseen attack
illumination normalization

期刊

IEEE Transactions on Multimedia 封面图
IEEE Transactions on Multimedia
IF:
9.7
论文数:
4.5K
被引数:
2.4W

机构

N
Nanyang Technological University
学者数:
4.9W
论文数: 4.8W
被引数: 8.1W
C
City University of Hong Kong
学者数:
2.3W
论文数: 3.0W
被引数: 6.1W
S
south china university of technology
学者数:
6.8W
论文数: 5.1W
被引数: 85
学者 查看更多机构
引用论文

引用论文

Histologic Findings of Corneal Buttons in Decompensated Corneas With Toxic Anterior Segment Syndrome After Cataract Surgery
err2013-10-01
err0
PREAI
errOsman Sevki Arslan; Zeki Tunc; Didar Ucar; Ismail Seckin; Erdogan Cicik; Hande Kalem; Sadik Sencan; Mustafa Hepokur
err分享
err收藏
Detection of Listeria monocytogenes in Fried Fish, Processing Slab and Tools
err2017-06-30
err0
errOAAI
errİbrahim Adeshına; Mozeedah Abdulwahab; Yusuf Adetunji Adewale; Sa'adu Bala Suleıman; Lateef Oloyede Tıamıyu
err分享
err收藏
err分享
err收藏
Progressive Transfer Learning for Face Anti-Spoofing
err2021-01-01
err44
PREAI
errQuan, Ruijie; Wu, Yu; Yu, Xin; Yang, Yi
err分享
err收藏
err分享
err收藏
Leveraging Shape, Reflectance and Albedo From Shading for Face Presentation Attack Detection
err2020-01-01
err27
PREAI
errPinto, Allan; Goldenstein, Siome; Ferreira, Alexandre; Carvalho, Tiago; Pedrini, Helio; Rocha, Anderson
err分享
err收藏
学者 查看更多内容