TY - JOUR
T1 - Thermal Face Generation using StyleGAN
AU - HERMOSILLA VIGNEAU, GABRIEL ENRIQUE
AU - Tapia, Diego Ignacio Henriquez
AU - ALLENDE CID, HÉCTOR GABRIEL
AU - FARIAS CASTRO, GONZALO ALBERTO
AU - VERA ROJAS, ESTEBAN MAURICIO
N1 - Publisher Copyright:
CCBY
PY - 2021
Y1 - 2021
N2 - This article proposes the use of generative adversarial networks (GANs) via StyleGAN2 to create high-quality synthetic thermal images and obtain training data to build thermal face recognition models using deep learning.We employed different variants of StyleGAN2, incorporating the new improved version of StyleGAN that uses adaptive discriminator augmentation (ADA). In addition, three different thermal databases from the literature were employed to train a thermal face detector based on YOLOv3 and to train StyleGAN2 and its variants, evaluating different metrics. The synthetic thermal database was built using GANSpace to manipulate the intermediate latent space w of StyleGAN2 and obtain images with different characteristics, such as eyeglasses, rotation, beards, etc. We carried out the training of 6 pretrained deep learning models for face recognition to validate the use of our synthetic thermal database, obtaining 99.98% accuracy for classifying synthetic thermal face images.
AB - This article proposes the use of generative adversarial networks (GANs) via StyleGAN2 to create high-quality synthetic thermal images and obtain training data to build thermal face recognition models using deep learning.We employed different variants of StyleGAN2, incorporating the new improved version of StyleGAN that uses adaptive discriminator augmentation (ADA). In addition, three different thermal databases from the literature were employed to train a thermal face detector based on YOLOv3 and to train StyleGAN2 and its variants, evaluating different metrics. The synthetic thermal database was built using GANSpace to manipulate the intermediate latent space w of StyleGAN2 and obtain images with different characteristics, such as eyeglasses, rotation, beards, etc. We carried out the training of 6 pretrained deep learning models for face recognition to validate the use of our synthetic thermal database, obtaining 99.98% accuracy for classifying synthetic thermal face images.
KW - Data models
KW - Databases
KW - Deep Learning
KW - Deep learning
KW - Face recognition
KW - Generative adversarial networks
KW - Generative Adversarial Networks
KW - Generators
KW - StyleGAN2
KW - thermal face recognition
KW - Training
UR - http://www.scopus.com/inward/record.url?scp=85107386611&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2021.3085423
DO - 10.1109/ACCESS.2021.3085423
M3 - Article
AN - SCOPUS:85107386611
JO - IEEE Access
JF - IEEE Access
SN - 2169-3536
ER -