Next Article in Journal
360°-Based Virtual Field Trips to Waterworks in Higher Education
Previous Article in Journal
Smart Interconnected Infrastructures for Security and Protection: The DESMOS Project
Previous Article in Special Issue
Evaluating Impact of Race in Facial Recognition across Machine Learning and Deep Learning Algorithms
Article

Feature Focus: Towards Explainable and Transparent Deep Face Morphing Attack Detectors

1
Department of Vision and Imaging Technologies, Fraunhofer Heinrich-Hertz-Institute, 10587 Berlin, Germany
2
Department of Visual Computing, Humboldt Universität zu Berlin, 10117 Berlin, Germany
*
Author to whom correspondence should be addressed.
This paper is an extended version of our paper published in WACV xAI4Biometrics Workshop 2021.
Academic Editor: Paolo Bellavista
Computers 2021, 10(9), 117; https://doi.org/10.3390/computers10090117
Received: 13 August 2021 / Revised: 6 September 2021 / Accepted: 14 September 2021 / Published: 18 September 2021
(This article belongs to the Special Issue Explainable Artificial Intelligence for Biometrics 2021)
Detecting morphed face images has become an important task to maintain the trust in automated verification systems based on facial images, e.g., at automated border control gates. Deep Neural Network (DNN)-based detectors have shown remarkable results, but without further investigations their decision-making process is not transparent. In contrast to approaches based on hand-crafted features, DNNs have to be analyzed in complex experiments to know which characteristics or structures are generally used to distinguish between morphed and genuine face images or considered for an individual morphed face image. In this paper, we present Feature Focus, a new transparent face morphing detector based on a modified VGG-A architecture and an additional feature shaping loss function, as well as Focused Layer-wise Relevance Propagation (FLRP), an extension of LRP. FLRP in combination with the Feature Focus detector forms a reliable and accurate explainability component. We study the advantages of the new detector compared to other DNN-based approaches and evaluate LRP and FLRP regarding their suitability for highlighting traces of image manipulation from face morphing. To this end, we use partial morphs which contain morphing artifacts in predefined areas only and analyze how much of the overall relevance each method assigns to these areas. View Full-Text
Keywords: face morphing attacks; DNN explainability; face image forgery detection face morphing attacks; DNN explainability; face image forgery detection
Show Figures

Figure 1

MDPI and ACS Style

Seibold, C.; Hilsmann, A.; Eisert, P. Feature Focus: Towards Explainable and Transparent Deep Face Morphing Attack Detectors. Computers 2021, 10, 117. https://doi.org/10.3390/computers10090117

AMA Style

Seibold C, Hilsmann A, Eisert P. Feature Focus: Towards Explainable and Transparent Deep Face Morphing Attack Detectors. Computers. 2021; 10(9):117. https://doi.org/10.3390/computers10090117

Chicago/Turabian Style

Seibold, Clemens, Anna Hilsmann, and Peter Eisert. 2021. "Feature Focus: Towards Explainable and Transparent Deep Face Morphing Attack Detectors" Computers 10, no. 9: 117. https://doi.org/10.3390/computers10090117

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop