Cookies helfen uns bei der Bereitstellung unserer Dienste. Durch die Nutzung unserer Dienste erklären Sie sich damit einverstanden, dass wir Cookies setzen.

Cuvillier Verlag

30 Jahre Kompetenz im wissenschaftlichen Publizieren
Internationaler Fachverlag für Wissenschaft und Wirtschaft

Cuvillier Verlag

De En Es
Active Multispectral SWIR Imaging for Reliable Skin Detection and Face Verification

EUR 0,00

EUR 0,00

Active Multispectral SWIR Imaging for Reliable Skin Detection and Face Verification

Holger Steiner (Autor)


Inhaltsverzeichnis, PDF (55 KB)
Leseprobe, PDF (1,5 MB)

ISBN-13 (Printausgabe) 9783736994508
ISBN-13 (E-Book) 9783736984509
Sprache Englisch
Seitenanzahl 202
Umschlagkaschierung matt
Auflage 1. Aufl.
Erscheinungsort Göttingen
Promotionsort Siegen
Erscheinungsdatum 10.01.2017
Allgemeine Einordnung Dissertation
Fachbereiche Informatik
Schlagwörter Computer Vision, Multispectral Imaging, Skin Detection, Biometrics, Face Recognition, Anti-Spoofing

The detection of human skin in images is a very desirable feature for applications such as biometric face recognition, which is becoming more frequently used for, e.g., automated border or access control. However, distinguishing real skin from other materials based on imagery captured in the visual spectrum alone and in spite of varying skin types and lighting conditions can be dicult and unreliable. Therefore, spoofing attacks with facial disguises or masks are still a serious problem for state of the art face recognition algorithms.
This dissertation presents a novel approach for reliable skin detection based on spectral remission properties in the short-wave infrared (SWIR) spectrum and proposes a cross-modal method that enhances existing solutions for face verification to ensure the authenticity of a face even in the presence of partial disguises or masks. Furthermore, it presents a reference design and the necessary building blocks for an active multispectral camera system that implements this approach, as well as an in-depth evaluation.
The system acquires four-band multispectral images within T = 50ms. Using a machine-learning-based classifier, it achieves unprecedented skin detection accuracy, even in the presence of skin-like materials used for spoofing attacks. Paired with a commercial face recognition software, the system successfully rejected all evaluated attempts to counterfeit a foreign face.