TU Darmstadt / ULB / TUbiblio

Detecting Face Morphing Attacks by Analyzing the Directed Distances of Facial Landmarks Shifts

Damer, Naser and Boller, Viola and Wainakh, Yaza and Boutros, Fadi and Terhörst, Philipp and Braun, Andreas and Kuijper, Arjan (2019):
Detecting Face Morphing Attacks by Analyzing the Directed Distances of Facial Landmarks Shifts.
In: Pattern Recognition, Cham, Springer, In: 40th German Conference, GCPR, Stuttgart, Germany, October 9-12, 2018, In: Lecture Notes in Computer Science (LNCS), 11269, ISSN 0302-9743,
ISBN 978-3-030-12938-5,
DOI: 10.1007/978-3-030-12939-2_36,
[Online-Edition: https://doi.org/10.1007/978-3-030-12939-2_36],
[Conference or Workshop Item]

Abstract

Face morphing attacks create face images that are verifiable to multiple identities. Associating such images to identity documents lead to building faulty identity links, causing attacks on operations like border crossing. Most of previously proposed morphing attack detection approaches directly classified features extracted from the investigated image. We discuss the operational opportunity of having a live face probe to support the morphing detection decision and propose a detection approach that take advantage of that. Our proposed solution considers the facial landmarks shifting patterns between reference and probe images. This is represented by the directed distances to avoid confusion with shifts caused by other variations. We validated our approach using a publicly available database, built on 549 identities. Our proposed detection concept is tested with three landmark detectors and proved to outperform the baseline concept based on handcrafted and transferable CNN features.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Damer, Naser and Boller, Viola and Wainakh, Yaza and Boutros, Fadi and Terhörst, Philipp and Braun, Andreas and Kuijper, Arjan
Title: Detecting Face Morphing Attacks by Analyzing the Directed Distances of Facial Landmarks Shifts
Language: English
Abstract:

Face morphing attacks create face images that are verifiable to multiple identities. Associating such images to identity documents lead to building faulty identity links, causing attacks on operations like border crossing. Most of previously proposed morphing attack detection approaches directly classified features extracted from the investigated image. We discuss the operational opportunity of having a live face probe to support the morphing detection decision and propose a detection approach that take advantage of that. Our proposed solution considers the facial landmarks shifting patterns between reference and probe images. This is represented by the directed distances to avoid confusion with shifts caused by other variations. We validated our approach using a publicly available database, built on 549 identities. Our proposed detection concept is tested with three landmark detectors and proved to outperform the baseline concept based on handcrafted and transferable CNN features.

Title of Book: Pattern Recognition
Series Name: Lecture Notes in Computer Science (LNCS)
Volume: 11269
Place of Publication: Cham
Publisher: Springer
ISBN: 978-3-030-12938-5
Uncontrolled Keywords: Biometrics, Face recognition, Spoofing attacks
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: 40th German Conference, GCPR
Event Location: Stuttgart, Germany
Event Dates: October 9-12, 2018
Date Deposited: 26 Jun 2019 08:54
DOI: 10.1007/978-3-030-12939-2_36
Official URL: https://doi.org/10.1007/978-3-030-12939-2_36
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item