Novel network proposed to enhance underwater image quality

The overall architecture of the LFT-DGAN network
Credit: WANG Liusan

Recently, the team led by Prof. WANG Rujing and WANG Liusan from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences, established a Learnable Full-frequency Transformer Dual Generative Adversarial Network (LFT-DGAN) to address the issue of underwater image quality degradation caused by various interferences.

The research results were published in Frontiers in Marine Science.

Underwater image enhancement technology aims to optimize the quality of underwater images and meet the diverse needs of marine scientific research, underwater robots and object recognition. Due to the unique underwater environment, noise and colour deviation often affect images, making enhancement extremely difficult. Researchers must continue exploring and innovating to improve the quality of underwater images.

This study used the knowledge of reversible convolution and adversarial neural networks to establish a dual-generative adversarial neural network model of the full-frequency transformer and verified its effectiveness by comparing multiple underwater image experimental data.

With the help of this model,researchers used image decomposition technology with reversible convolution for the first time to accurately separate the different frequency features of the image.

In addition, the study used an advanced transformer model that can learn to improve the interaction and integration of different types of information. They also created a dual-domain discriminator to better capture and analyze the frequency characteristics of the images.

“Our research results and methods have provided a solid theoretical foundation and strong support for the subsequent research and development of underwater image enhancement.” said Wang Liusan.

Journal: Frontiers in Marine Science
Article Title: Discrimination of internal crack for rice seeds using near infrared spectroscopy
Article Publication Date: 1-Jun-2024

Media Contact

Weiwei Zhao
Hefei Institutes of Physical Science, Chinese Academy of Sciences
annyzhao@ipp.ac.cn
Office: 86-551-655-91206

Media Contact

Weiwei Zhao
Hefei Institutes of Physical Science, Chinese Academy of Sciences

All latest news from the category: Physics and Astronomy

This area deals with the fundamental laws and building blocks of nature and how they interact, the properties and the behavior of matter, and research into space and time and their structures.

innovations-report provides in-depth reports and articles on subjects such as astrophysics, laser technologies, nuclear, quantum, particle and solid-state physics, nanotechnologies, planetary research and findings (Mars, Venus) and developments related to the Hubble Telescope.

Back to home

Comments (0)

Write a comment

Newest articles

World’s first method

Successful surgery for a rare congenital heart disease “scimitar syndrome”. Scimitar syndrome, a rare congenital heart disease, involves an anomalous pulmonary venous return where the right pulmonary veins return to…

Improving HIV treatment in children and adolescents – the right way!

Globally, around 2.6 million children and adolescents are currently living with HIV, the majority of them in Africa. These young people are much more likely to experience treatment failure than…

Study shows promise for a universal influenza vaccine

OHSU-led research uses innovative vaccine platform to target interior of virus; scientists validate theory using 1918 flu virus. New research led by Oregon Health & Science University reveals a promising…

Partners & Sponsors