TY  - JOUR
AU  - Andre Litvin
AU  - Kamal Nasrollahi
AU  - Sergio Escalera
AU  - Cagri Ozcinar
AU  - Thomas B. Moeslund
AU  - Gholamreza Anbarjafari
PY  - 2019//
TI  - A Novel Deep Network Architecture for Reconstructing RGB Facial Images from Thermal for Face Recognition
T2  - MTAP
JO  - Multimedia Tools and Applications
SP  - 25259–25271
VL  - 78
IS  - 18
KW  - Fully convolutional networks
KW  - FusionNet
KW  - Thermal imaging
KW  - Face recognition
N2  - This work proposes a fully convolutional network architecture for RGB face image generation from a given input thermal face image to be applied in face recognition scenarios. The proposed method is based on the FusionNet architecture and increases robustness against overfitting using dropout after bridge connections, randomised leaky ReLUs (RReLUs), and orthogonal regularization. Furthermore, we propose to use a decoding block with resize convolution instead of transposed convolution to improve final RGB face image generation. To validate our proposed network architecture, we train a face classifier and compare its face recognition rate on the reconstructed RGB images from the proposed architecture, to those when reconstructing images with the original FusionNet, as well as when using the original RGB images. As a result, we are introducing a new architecture which leads to a more accurate network.
UR  - https://link.springer.com/article/10.1007/s11042-019-7667-4
N1  - HuPBA; no menciona
ID  - Andre Litvin2019
ER  -