Hybird Single-Multiple Frame Super-Resolution Reconstruction of Video Face Image

2019 ◽  
pp. 773-784
Author(s):  
Jianbin Gao ◽  
Huan Tang ◽  
James C. Gee
Keyword(s):  
Super Resolution ◽  
Face Image ◽  
Multiple Frame

Single face image super-resolution using local training networks

2017 ◽  
Author(s):  
Peiqing Ni ◽  
Dongping Zhang ◽  
Kui Hu ◽  
Changxing Jing ◽  
Li Yang
Keyword(s):  
Super Resolution ◽  
Face Image ◽  
Single Face ◽  
Image Super Resolution

scholarly journals Photon-limited face image super-resolution based on deep learning

2018 ◽  
Vol 26 (18) ◽  
pp. 22773 ◽  
Author(s):  
Zhouzhou Niu ◽  
Jianhong Shi ◽  
Lei Sun ◽  
Yan Zhu ◽  
Jianping Fan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Super Resolution ◽  
Face Image ◽  
Image Super Resolution

scholarly journals Shuffle block SRGAN for face image super-resolution reconstruction

2020 ◽  
Vol 53 (7-8) ◽  
pp. 1429-1439
Author(s):  
Ziwei Zhang ◽  
Yangjing Shi ◽  
Xiaoshi Zhou ◽  
Hongfei Kan ◽  
Juan Wen
Keyword(s):  
Face Recognition ◽  
Learning Strategy ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Super Resolution ◽  
Face Image ◽  
Low Resolution ◽  
Index Method ◽  
Face Features ◽  
Image Super Resolution

When low-resolution face images are used for face recognition, the model accuracy is substantially decreased. How to recover high-resolution face features from low-resolution images precisely and efficiently is an essential subtask in face recognition. In this study, we introduce shuffle block SRGAN, a new image super-resolution network inspired by the SRGAN structure. By replacing the residual blocks with shuffle blocks, we can achieve efficient super-resolution reconstruction. Furthermore, by considering the generated image quality in the loss function, we can obtain more realistic super-resolution images. We train and test SB-SRGAN in three public face image datasets and use transfer learning strategy during the training process. The experimental results show that shuffle block SRGAN can achieve desirable image super-resolution performance with respect to visual effect as well as the peak signal-to-noise ratio and structure similarity index method metrics, compared with the performance attained by the other chosen deep-leaning models.

Sign in / Sign up

Export Citation Format

Share Document