TY - GEN
T1 - Closed-set thermal face recognition via the synthesis approach
AU - Girshkin, Oren
AU - Yitzhaky, Yitzhak
N1 - Publisher Copyright:
© 2021 SPIE
PY - 2021/1/1
Y1 - 2021/1/1
N2 - Thermal face recognition has various applications in security, video-surveillance, military and government industries, etc. In contrast to the visible-light domain case, there is a lack of sufficiently large databases of thermal-face images. Therefore, it is difficult to construct a good face recognition system directly through learning procedures. We address this problem by using the synthesis approach, in which artificial visible-domain images of faces are generated from thermal face images and then identified in the visible-light domain. The generation of the artificial face images is done using a conditional Generative Adversarial Network, and the face identification is done by another, separate, deep neural network. Generating visible face images from thermal ones using DNNs requires large datasets of pairs of thermal and visible face images of the same persons, taken from the same position, time and imaging conditions, with two different cameras. The available datasets of such pairs are of relatively very low amount of subjects. Therefore, as in other similar studies, we approach this problem as a closed-set face recognition task, in which all testing identities are predefined in the training set, and train the face identification network using both the real and the synthesized images.
AB - Thermal face recognition has various applications in security, video-surveillance, military and government industries, etc. In contrast to the visible-light domain case, there is a lack of sufficiently large databases of thermal-face images. Therefore, it is difficult to construct a good face recognition system directly through learning procedures. We address this problem by using the synthesis approach, in which artificial visible-domain images of faces are generated from thermal face images and then identified in the visible-light domain. The generation of the artificial face images is done using a conditional Generative Adversarial Network, and the face identification is done by another, separate, deep neural network. Generating visible face images from thermal ones using DNNs requires large datasets of pairs of thermal and visible face images of the same persons, taken from the same position, time and imaging conditions, with two different cameras. The available datasets of such pairs are of relatively very low amount of subjects. Therefore, as in other similar studies, we approach this problem as a closed-set face recognition task, in which all testing identities are predefined in the training set, and train the face identification network using both the real and the synthesized images.
KW - Conditional generative adversarial network
KW - Thermal face recognition
KW - Thermal-to visible synthesis
UR - http://www.scopus.com/inward/record.url?scp=85118831741&partnerID=8YFLogxK
U2 - 10.1117/12.2600521
DO - 10.1117/12.2600521
M3 - Conference contribution
AN - SCOPUS:85118831741
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies V
A2 - Bouma, H.
A2 - Prabhu, R.
A2 - Stokes, R. J.
A2 - Yitzhaky, Y.
PB - SPIE
T2 - Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies V 2021
Y2 - 13 September 2021 through 17 September 2021
ER -