Facial Image Super Resolution Using Weighted Patch Pairs

Super-resolution methods for facial image via representation learning scheme have become very effective methods due to their efficiency. The key problem for the super-resolution of facial image is to reveal the latent relationship between the low-resolution ( LR ) and the corresponding high-resolution ( HR ) training patch pairs. To simultaneously utilize the contextual information of the target position and the manifold structure of the primitive HR space, in this work, we design a robust context-patch facial image super-resolution scheme via a kernel locality-constrained coupled-layer regression (KLC2LR) scheme to obtain the desired HR version from the acquired LR image. Here, KLC2LR proposes to acquire contextual surrounding patches to represent the target patch and adds an HR layer constraint to compensate the detail information. Additionally, KLC2LR desires to acquire more high-frequency information by searching for nearest neighbors in the HR sample space. We also utilize kernel function to map features in original low-dimensional space into a high-dimensional one to obtain potential nonlinear characteristics. Our compared experiments in the noisy and noiseless cases have verified that our suggested methodology performs better than many existing predominant facial image super-resolution methods.

Download Full-text

Facial image super-resolution guided by adaptive geometric features

EURASIP Journal on Wireless Communications and Networking ◽

10.1186/s13638-020-01760-y ◽

2020 ◽

Vol 2020 (1) ◽

Author(s):

Zhenfeng Fan ◽

Xiyuan Hu ◽

Chen Chen ◽

Xiaolian Wang ◽

Silong Peng

Keyword(s):

Super Resolution ◽

Geometric Features ◽

Facial Image ◽

Image Super Resolution

Download Full-text

Identifying Facemask-wearing Condition Using Image Super-Resolution with Classification Network to Prevent COVID-19

10.21203/rs.3.rs-28668/v1 ◽

2020 ◽

Cited By ~ 1

Author(s):

BOSHENG QIN ◽

DONGXIAO LI

Keyword(s):

Super Resolution ◽

Face Mask ◽

Classification Problem ◽

Automatic Identification ◽

Classification Methods ◽

Facial Image ◽

Infectious Disease Control ◽

Global Pandemic ◽

Public Dataset ◽

Image Super Resolution

Abstract Rapid worldwide spread of Coronavirus Disease 2019 (COVID 19) has resulted in a global pandemic. Correct facemask wearing is valuable in infectious disease control, but the effectiveness of facemasks has been diminished mostly due to improper wearing. However, there have not been any published reports on the automatic identification of facemask wearing conditions. In this study, we developed a new facemask wearing condition identification method in combination with image super resolution with classification network (SRCNet) SRCNet), which quantified a three categories classification problem based on unconstrained 2D facial image images. The proposed algorithm contained four main steps: image pre processing, face detection and crop, image super resolution, and face mask wearing conditions identification. Our method was trained and evaluated on public dataset Medical Masks Dataset containing 3835 images with 671 images of no facemask wearing, 134 images of incorrect facemask wearing, and 3030 images of correct facemask wearing. Finally, the proposed SRCNet achieved 98.70% accuracy and outperformed traditional end to end image classification methods using deep learning without image super resolution by over 1.5 in kappa. Our findings indicate that the proposed SRCNet could achieve high accuracy identification in facemask wearing conditions , which have potential application in epidemic prevention involving COVID 19.

Download Full-text