TY - GEN
T1 - Anti-spoofing face recognition using infrared structure light
AU - Sun, Shengtao
AU - Tian, Yue
AU - Tang, Ying
AU - Wu, Ben
N1 - Funding Information:
We proposed and demonstrated an anti-spoofing method for face recognition that can detect potential 3D printing spoofing and make up materials. From the disguised faces captured, we can reconstruct the spatial structure of the face and also analyze the reflection information on IR. Reconstruction of the face is obtained by triangulation of the images marked by structure light pattern and the suspicious are is cropped out by segmentation using CNN. The system is demonstrated to detect the artificial materials such as latex and foundation which are common for facial disguise. This research is supported by NEC Laboratories America, INC. and NSF Grant No.1610164.
Publisher Copyright:
© OSA 2020 © 2020 The Author(s)
PY - 2020/9/14
Y1 - 2020/9/14
N2 - We demonstrate an anti-spoofing face recognition system that is able to differentiate real human face with 3D printed materials. Face images captured in infrared structure light are analyzed for surface materials and spatial structure.
AB - We demonstrate an anti-spoofing face recognition system that is able to differentiate real human face with 3D printed materials. Face images captured in infrared structure light are analyzed for surface materials and spatial structure.
UR - http://www.scopus.com/inward/record.url?scp=85106000798&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85106000798&partnerID=8YFLogxK
U2 - 10.1364/FIO.2020.FW1F.3
DO - 10.1364/FIO.2020.FW1F.3
M3 - Conference contribution
AN - SCOPUS:85106000798
T3 - Optics InfoBase Conference Papers
BT - Frontiers in Optics - Proceedings Frontiers in Optics / Laser Science, Part of Frontiers in Optics + Laser Science APS/DLS, FiO 2020
PB - Optica Publishing Group (formerly OSA)
T2 - 2020 Frontiers in Optics Conference, FiO 2020
Y2 - 14 September 2020 through 17 September 2020
ER -