A Novel Deep Learning Architecture with Image Diffusion for Robust Face Presentation Attack Detection

Face presentation attack detection (PAD) is considered to be an essential and critical step in modern face recognition systems. Face PAD aims at exposing an imposter or an unauthorized person seeking to deceive the authentication system. Presentation attacks are typically made using a fake ID throug...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2023-01, Vol.11, p.1-1
Main Authors: Alassafi, Madini O., Ibrahim, Muhammad Sohail, Naseem, Imran, AlGhamdi, Rayed, Alotaibi, Reem, Kateb, Faris A., Oqaibi, Hadi Mohsen, Alshdadi, Abdulrahman A., Yusuf, Syed Adnan
Format: Article
Language:English
Subjects:
Anti-spoofing
Artificial neural networks
Convolutional neural networks
Deep learning
Diffusion processes
face liveness detection
face presentation attack detection
Face recognition
Feature extraction
Interpolation
interpolation-based image diffusion
Machine learning
Optical flow
Spoofing
Task analysis
Three-dimensional displays
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Face presentation attack detection (PAD) is considered to be an essential and critical step in modern face recognition systems. Face PAD aims at exposing an imposter or an unauthorized person seeking to deceive the authentication system. Presentation attacks are typically made using a fake ID through a digital/printed photograph, video, paper mask, 3D mask, and make-up etc. In this research, we propose a novel face PAD solution using an interpolation-based image diffusion augmented by transfer learning of a MobileNet convolutional neural network. The proposed interpolation-based image diffusion method and face PAD approach, implemented in a single framework, shows promising results on various anti-spoofing databases. The experimental results illustrate that the proposed face PAD method shows superior performance compared to most of the state-of-the-art methods.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2023.3285826