University of Oulu

A. Liu et al., "Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection," in IEEE Transactions on Information Forensics and Security, vol. 17, pp. 2497-2507, 2022, doi: 10.1109/TIFS.2022.3188149

Contrastive context-aware learning for 3D high-fidelity mask face presentation attack detection

Saved in:
Author: Liu, Ajian1; Zhao, Chenxu2; Yu, Zitong3;
Organizations: 1National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China
2Mininglamp Academy of Sciences, Mininglamp Technology, Beijing, China
3Faculty of Information Technology and Electrical Engineering, University of Oulu, Oulu, Finland
4Faculty of Innovation Engineering, Macau University of Science and Technology (MUST), Av. Wai Long, Macau, China
5School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China
6Baidu Research and National Engineering Laboratory for Deep Learning Technology and Application, Institute of Deep Learning, Beijing, China
7Computer Vision Centre (CVC), Universitat de Barcelona (UB), Barcelona, Spain
8Department of Computer Science and Technology, Tsinghua University, Beijing, China
9Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong, China
10AI Lab, School of Engineer, Westlake University, Hangzhou, China
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 14.4 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2022
Publish Date: 2023-04-06


Face presentation attack detection (PAD) is essential to secure face recognition systems primarily from high-fidelity mask attacks. Most existing 3D mask PAD benchmarks suffer from several drawbacks: 1) a limited number of mask identities, types of sensors, and a total number of videos; 2) low-fidelity quality of facial masks. Basic deep models and remote photoplethysmography (rPPG) methods achieved acceptable performance on these benchmarks but still far from the needs of practical scenarios. To bridge the gap to real-world applications, we introduce a large-scale High- Fidelity Mask dataset, namely HiFiMask. Specifically, a total amount of 54,600 videos are recorded from 75 subjects with 225 realistic masks by 7 new kinds of sensors. Along with the dataset, we propose a novel C ontrastive C ontext-aware L earning (CCL) framework. CCL is a new training methodology for supervised PAD tasks, which is able to learn by leveraging rich contexts accurately (e.g., subjects, mask material and lighting) among pairs of live faces and high-fidelity mask attacks. Extensive experimental evaluations on HiFiMask and three additional 3D mask datasets demonstrate the effectiveness of our method. The codes and dataset will be released soon.

see all

Series: IEEE transactions on information forensics and security
ISSN: 1556-6013
ISSN-E: 1556-6021
ISSN-L: 1556-6013
Volume: 17
Pages: 2497 - 2507
DOI: 10.1109/tifs.2022.3188149
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Funding: This work was supported in part by the National Key Research and Development Plan under Grant 2021YFF0602103, in part by the External Cooperation Key Project of Chinese Academy of Sciences (173211KYSB20200002), in part by the Chinese National Natural Science Foundation under Project 61876179 and Project 61961160704, in part by the Science and Technology Development Fund of Macau under Project 0070/2020/AMJ, in part by the Open Research Projects of Zhejiang Laboratory under Project 2021KH0AB07, in part by the Spanish Project (PID2019-105093GB-I00), in part by the Institución Catalana de Investigación y Estudios Avanzados (ICREA) under the ICREA Academia Program, and in part by the InnoHK Program.
Copyright information: © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.