Quality Matters: Boosting Face Presentation Attack Detection With Image Quality Metrics
Open Access
- 1 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 94654-94672
Abstract
Face Presentation Attack Detection (PAD) is critical for enhancing the security of facial recognition systems against sophisticated attacks. This study explores the use of general Image Quality Assessment (IQA) methods in face PAD, offering a new approach that deviates from traditional, face-specific PAD techniques. Our evaluation of eight widely-used IQA methods across four PAD databases is structured around three distinct experimental protocols. Preliminary findings indicate that the general IQA methods are not fully effective in differentiating between genuine and attack samples, highlighting the need for modification. Nonetheless, a notable enhancement in performance is observed following the re-training of these methods using PAD datasets, bringing their effectiveness in line with that of advanced traditional PAD methods. This study provides evidence for the potential of general IQA in bolstering the resilience of face recognition systems against presentation attacks.Keywords
Funding Information
- National Natural Science Foundation of China (62106228)
- Natural Science Foundation of Zhejiang Province (LQ22F020003)
- Public Welfare Technology Research Program of Zhejiang Provincial (LGF20F020005, LGG22E050042)
- Natural Science Foundation of Ningbo Municipality (2021J175)
- Ningbo Key Research and Development Plan (2023Z035, 2023Z003)
- Ningbo Yongjiang Talent Introduction Program 2021
This publication has 86 references indexed in Scilit:
- Effective Presentation Attack Detection Driven by Face Related Task2022
- Face spoofing detection based on chromatic ED-LBP texture featureMultimedia Systems, 2020
- CelebA-Spoof: Large-Scale Face Anti-spoofing Dataset with Rich Annotations2020
- Perceptual image quality assessment: a surveyScience China Information Sciences, 2020
- SLNet: Stereo face liveness detection via dynamic disparity-maps and convolutional neural networkExpert Systems with Applications, 2020
- Introduction to Face Presentation Attack Detection2019
- Face Anti-spoofing via Deep Local Binary Pattern2019
- No-reference image quality assessment based on spatial and spectral entropiesSignal Processing: Image Communication, 2014
- LBP − TOP Based Countermeasure against Face Spoofing Attacks2013
- Face Liveness Detection from a Single Image with Sparse Low Rank Bilinear Discriminative Model2010