Active Multispectral SWIR Imaging for Reliable Skin Detection and Face Verification - Steiner, Holger
58,00 €
inkl. MwSt.
Versandkostenfrei*
Versandfertig in 1-2 Wochen
payback
0 °P sammeln
  • Broschiertes Buch

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…mehr

Andere Kunden interessierten sich auch für
Produktbeschreibung
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.
Autorenporträt
Holger Steiner, born in 1982 in Bonn, Germany, studied Computer Science and Autonomous Systems at the Bonn-Rhein-Sieg University of Applied Sciences (BRSU) and graduated with the Master of Science degree in 2008. Afterwards he started working as a research scientist at the Institute for Occupational Safety and Health of the German Social Accident Insurance (DGUV), where he continued working on his master thesis topic and developed intelligent sensor systems for the acquisition of physiological data and the evaluation of multicausal strain at mobile workplaces. In 2009, he returned to the BRSU as a research scientist at the Institute for Safety and Security Research. He was involved in several successfull research projects in the field of optical sensor and camera systems. In 2011, he became an external member of the DFG Research Training Group 1564 ¿Imaging New Modalities¿ at the University of Siegen and began working on his Ph.D. topic, the reliable detection of human skin using multispectral imaging in the short-wave infrared spectrum. He finished his Ph.D. in 2016 and left the University to work as a research engineer in the industry. http://www.grk1564.uni-siegen.de/de/steiner-holger