Multiple Connected Residual Network for Image Enhancement on Smartphones

2019 ◽  
pp. 182-196 ◽  
Author(s):  
Jie Liu ◽  
Cheolkon Jung
Keyword(s):  
Image Enhancement ◽  
Residual Network

scholarly journals Real‐time classification on oral ulcer images with residual network and image enhancement

2021 ◽  
Author(s):  
Jianbin Guo ◽  
Haolin Wang ◽  
Xingsi Xue ◽  
Mengting Li ◽  
Zhongxiong Ma
Keyword(s):  
Real Time ◽  
Image Enhancement ◽  
Oral Ulcer ◽  
Residual Network ◽  
Real Time Classification

scholarly journals Underwater image enhancement via LBP‐based attention residual network

2021 ◽  
Author(s):  
ZhiXiong Huang ◽  
Jinjiang Li ◽  
Zhen Hua
Keyword(s):  
Image Enhancement ◽  
Residual Network ◽  
Underwater Image

Learning Multi-scale Retinex with Residual Network for Low-Light Image Enhancement

2020 ◽  
pp. 291-302
Author(s):  
Long Ma ◽  
Jie Lin ◽  
Jingjie Shang ◽  
Wei Zhong ◽  
Xin Fan ◽  
...  
Keyword(s):  
Image Enhancement ◽  
Residual Network ◽  
Low Light ◽  
Multi Scale ◽  
Light Image

scholarly journals Underwater image enhancement via efficient generative adversarial network

2021 ◽  
Vol 51 (4) ◽  
Author(s):  
Xin Qian ◽  
Peng Ge
Keyword(s):  
Image Enhancement ◽  
Loss Function ◽  
State Of The Art ◽  
Residual Network ◽  
Kernel Size ◽  
Generative Adversarial Network ◽  
Qualitative And Quantitative ◽  
Adversarial Network ◽  
Underwater Image ◽  
Residual Block

Underwater image enhancement has been receiving much attention due to its significance in facilitating various marine explorations. Inspired by the generative adversarial network (GAN) and residual network (ResNet) in many vision tasks, we propose a simplified designed ResNet model based on GAN called efficient GAN (EGAN) for underwater image enhancement. In particular, for the generator of EGAN we design a new pair of convolutional kernel size for the residual block in the ResNet. Secondly, we abandon batch normalization (BN) after every convolution layer for faster training and less artifacts. Finally, a smooth loss function is introduced for halo-effect alleviation. Extensive qualitative and quantitative experiments show that our methods accomplish considerable improvements compared to the state-of-the-art methods.

Exploring Coronal Structures with SOHO

2000 ◽  
Vol 179 ◽  
pp. 403-406
Author(s):  
M. Karovska ◽  
B. Wood ◽  
J. Chen ◽  
J. Cook ◽  
R. Howard
Keyword(s):  
Solar Corona ◽  
Image Enhancement ◽  
Coronal Mass Ejections ◽  
Dynamical Evolution ◽  
Small Scale ◽  
Low Contrast ◽  
Contrast Structures ◽  
Scale Structures ◽  
Small Scale Structures ◽  
Coronal Structures

AbstractWe applied advanced image enhancement techniques to explore in detail the characteristics of the small-scale structures and/or the low contrast structures in several Coronal Mass Ejections (CMEs) observed by SOHO. We highlight here the results from our studies of the morphology and dynamical evolution of CME structures in the solar corona using two instruments on board SOHO: LASCO and EIT.

Maximum entropy algorithm applied to image enhancement

1980 ◽  
Vol 127 (5) ◽  
pp. 170 ◽  
Author(s):  
G.J. Daniell ◽  
S.F. Gull
Keyword(s):  
Maximum Entropy ◽  
Image Enhancement
Sign in / Sign up

Export Citation Format

Share Document