Face Anti-Spoofing Method Based on Residual Network with Channel Attention Mechanism

The face recognition system is vulnerable to spoofing attacks by photos or videos of a valid user face. However, edge degradation and texture blurring occur when non-living face images are used to attack the face recognition system. With this in mind, a novel face anti-spoofing method combines the r...

Full description

Saved in:
Bibliographic Details
Published in:Electronics (Basel) 2022-10, Vol.11 (19), p.3056
Main Authors: Kong, Yueping, Li, Xinyuan, Hao, Guangye, Liu, Chu
Format: Article
Language:English
Subjects:
Access control
Blurring
Data security
Datasets
Face recognition
Facial recognition technology
Feature extraction
Image contrast
Image enhancement
Machine learning
Methods
Network management systems
Neural networks
Object recognition
Spoofing
Texture
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The face recognition system is vulnerable to spoofing attacks by photos or videos of a valid user face. However, edge degradation and texture blurring occur when non-living face images are used to attack the face recognition system. With this in mind, a novel face anti-spoofing method combines the residual network and the channel attention mechanism. In our method, the residual network extracts the texture differences of features between face images. In contrast, the attention mechanism focuses on the differences of shadow and edge features located on nasal and cheek areas between living and non-living face images. It can assign weights to different filter features of the face image and enhance the ability of network extraction and expression of different key features in the nasal and cheek regions, improving detection accuracy. The experiments were performed on the public face anti-spoofing datasets of Replay-Attack and CASIA-FASD. We found the best value of the parameter r suitable for face anti-spoofing research is 16, and the accuracy of the method is 99.98% and 97.75%, respectively. Furthermore, to enhance the robustness of the method to illumination changes, the experiment was also performed on the datasets with light changes and achieved a good result.
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics11193056