TY - GEN
T1 - A deep-learning framework for concealed and unconcealed face analysis in submillimeter wave imaging
AU - Bergman, Noam
AU - Yildirim, Ihsan Ozan
AU - Sahin, Asaf Behzat
AU - Altan, Hakan
AU - Yitzhaky, Yitzhak
N1 - Publisher Copyright:
© COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.
PY - 2025/10/28
Y1 - 2025/10/28
N2 - This work presents a deep learning framework for sub-millimeter-wave (Sub-MMW) facial analysis that operates on active 340 GHz intensity images acquired from 20 identities in both concealed and unconcealed conditions over five head postures, including front-facing and yawed views, with approximately 35 images per condition per identity (1,400 total images). The framework addresses concealed-to-unconcealed face verification, head posture classification, and pixel-wise reconstruction of unconcealed from concealed observations, showing that task-tailored networks achieve strong performance mainly in verification, and posture recognition, while reproducing and extending a structural similarity (SSIM) sliding-window baseline for concealed-unconcealed verification reported for the same instrument class.
AB - This work presents a deep learning framework for sub-millimeter-wave (Sub-MMW) facial analysis that operates on active 340 GHz intensity images acquired from 20 identities in both concealed and unconcealed conditions over five head postures, including front-facing and yawed views, with approximately 35 images per condition per identity (1,400 total images). The framework addresses concealed-to-unconcealed face verification, head posture classification, and pixel-wise reconstruction of unconcealed from concealed observations, showing that task-tailored networks achieve strong performance mainly in verification, and posture recognition, while reproducing and extending a structural similarity (SSIM) sliding-window baseline for concealed-unconcealed verification reported for the same instrument class.
KW - Concealed Face Recognition
KW - Deep Learning
KW - Structural Similarity Index (SSIM)
KW - Sub-millimeter wave imaging
KW - Terahertz (THz) imaging
UR - https://www.scopus.com/pages/publications/105024849217
U2 - 10.1117/12.3070305
DO - 10.1117/12.3070305
M3 - Conference contribution
AN - SCOPUS:105024849217
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Artificial Intelligence for Security and Defence Applications III
A2 - Kuijf, Hugo J.
A2 - Prabhu, Radhakrishna
A2 - Yitzhaky, Yitzhak
PB - SPIE
T2 - 3rd Artificial Intelligence for Security and Defence Applications
Y2 - 16 September 2025 through 18 September 2025
ER -