Neural networks as a relevant and effective tool for image restoration. A study of the “super resolution” image restoration algorithm

2021 ◽  
Author(s):  
A. Ishmukhametova ◽  
R. Usmanov
Keyword(s):  
Neural Networks ◽  
Image Restoration ◽  
Super Resolution ◽  
Resolution Image ◽  
Restoration Algorithm

Confocal pore size measurement based on super-resolution image restoration

2014 ◽  
Vol 53 (25) ◽  
pp. 5694 ◽  
Author(s):  
Dali Liu ◽  
Yun Wang ◽  
Lirong Qiu ◽  
Xinyue Mao ◽  
Weiqian Zhao
Keyword(s):  
Image Restoration ◽  
Pore Size ◽  
Super Resolution ◽  
Size Measurement ◽  
Resolution Image

scholarly journals Single Image Super-Resolution Method Using CNN-Based Lightweight Neural Networks

2021 ◽  
Vol 11 (3) ◽  
pp. 1092
Author(s):  
Seonjae Kim ◽  
Dongsan Jun ◽  
Byung-Gyu Kim ◽  
Hunjoo Lee ◽  
Eunjun Rhee
Keyword(s):  
Neural Networks ◽  
Super Resolution ◽  
Learning Technologies ◽  
Feature Maps ◽  
Resolution Method ◽  
Resolution Image ◽  
Training Images ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
Similar Image Quality

There are many studies that seek to enhance a low resolution image to a high resolution image in the area of super-resolution. As deep learning technologies have recently shown impressive results on the image interpolation and restoration field, recent studies are focusing on convolutional neural network (CNN)-based super-resolution schemes to surpass the conventional pixel-wise interpolation methods. In this paper, we propose two lightweight neural networks with a hybrid residual and dense connection structure to improve the super-resolution performance. In order to design the proposed networks, we extracted training images from the DIVerse 2K (DIV2K) image dataset and investigated the trade-off between the quality enhancement performance and network complexity under the proposed methods. The experimental results show that the proposed methods can significantly reduce both the inference speed and the memory required to store parameters and intermediate feature maps, while maintaining similar image quality compared to the previous methods.

Sign in / Sign up

Export Citation Format

Share Document