The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Adversarial Reconstruction CNN for Illumination-Robust Frontal Face Image Recovery and Recognition
|
Author(s): Liping Yang (Key Laboratory of Optoelectronic Technology and Systems, MOE, Chongqing University, Chongqing, China), Bin Yang (Key Laboratory of Optoelectronic Technology and Systems, MOE, Chongqing University, Chongqing, China)and Xiaohua Gu (School of Electrical Engineering, Chongqing University of Science and Technology, Chongqing, China)
Copyright: 2021
Volume: 15
Issue: 2
Pages: 16
Source title:
International Journal of Cognitive Informatics and Natural Intelligence (IJCINI)
Editor(s)-in-Chief: Kangshun Li (South China Agricultural University, China)
DOI: 10.4018/IJCINI.20210401.oa2
Purchase
|
Abstract
This article proposes an adversarial reconstruction convolution neural network (ARCNN) for non-uniform illumination frontal face image recovery and recognition. The proposed ARCNN includes a reconstruction network and a discriminative network. The authors employ GAN framework to learn the reconstruction network in an adversarial manner. This article integrates gradient loss and perceptual loss terms, which are able to preserve the detailed and spatial structure image information, into the overall reconstruction loss function to constraint the reconstruction procedure. Experiments are conducted on the typical illumination-sensitive dataset, extended YaleB dataset. The reconstructed results demonstrate that the proposed ARCNN approach can remove the illumination and shadow information and recover natural uniform illuminated face image from non-uniform illuminated ones. Face recognition results on the extended YaleB dataset demonstrate that the proposed ARCNN reconstruction procedure can also preserve the discriminative information of face image for classification task.
Related Content
.
© 2024.
|
.
© 2024.
|
.
© 2024.
|
.
© 2024.
|
.
© 2024.
|
.
© 2024.
|
.
© 2024.
|
|
|