TY - GEN
T1 - Thermal to visible face recognition using deep autoencoders
AU - Kantarci, Alperen
AU - Ekenel, Hazim Kemal
N1 - Publisher Copyright:
© 2019 Gesellschaft fuer Informatik.
PY - 2019/9
Y1 - 2019/9
N2 - Visible face recognition systems achieve nearly perfect recognition accuracies using deep learning. However, in lack of light, these systems perform poorly. A way to deal with this problem is thermal to visible cross-domain face matching. This is a desired technology because of its usefulness in night time surveillance. Nevertheless, due to differences between two domains, it is a very challenging face recognition problem. In this paper, we present a deep autoencoder based system to learn the mapping between visible and thermal face images. Also, we assess the impact of alignment in thermal to visible face recognition. For this purpose, we manually annotate the facial landmarks on the Carl and EURECOM datasets. The proposed approach is extensively tested on three publicly available datasets: Carl, UND-X1, and EURECOM. Experimental results show that the proposed approach improves the state-of-the-art significantly. We observe that alignment increases the performance by around 2%. Annotated facial landmark positions in this study can be downloaded from the following link: github.com/Alpkant/Thermal-to-Visible-Face-Recognition-Using-Deep-Autoencoders.
AB - Visible face recognition systems achieve nearly perfect recognition accuracies using deep learning. However, in lack of light, these systems perform poorly. A way to deal with this problem is thermal to visible cross-domain face matching. This is a desired technology because of its usefulness in night time surveillance. Nevertheless, due to differences between two domains, it is a very challenging face recognition problem. In this paper, we present a deep autoencoder based system to learn the mapping between visible and thermal face images. Also, we assess the impact of alignment in thermal to visible face recognition. For this purpose, we manually annotate the facial landmarks on the Carl and EURECOM datasets. The proposed approach is extensively tested on three publicly available datasets: Carl, UND-X1, and EURECOM. Experimental results show that the proposed approach improves the state-of-the-art significantly. We observe that alignment increases the performance by around 2%. Annotated facial landmark positions in this study can be downloaded from the following link: github.com/Alpkant/Thermal-to-Visible-Face-Recognition-Using-Deep-Autoencoders.
KW - Autoencoders
KW - Convolutional neural networks
KW - Heterogeneous face recognition
KW - Thermal to visible matching
UR - http://www.scopus.com/inward/record.url?scp=85075901077&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075901077&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85075901077
T3 - 2019 International Conference of the Biometrics Special Interest Group, BIOSIG 2019 - Proceedings
BT - 2019 International Conference of the Biometrics Special Interest Group, BIOSIG 2019 - Proceedings
A2 - Bromme, Bromme
A2 - Busch, Christoph
A2 - Dantcheva, Antitza
A2 - Rathgeb, Christian
A2 - Uhl, Andreas
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 International Conference of the Biometrics Special Interest Group, BIOSIG 2019
Y2 - 18 September 2019 through 20 September 2019
ER -