Underwater Image Enhancement Based on Improved U-Net Convolutional Neural Network

Aiming at the problems of low contrast, dim and color distortion of underwater images caused by the attenuation and scattering of light in water propagation, an underwater image enhancement algorithm, which is based on a U-Net convolutional Neural Network is proposed. The algorithm consists of an im...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE 18th Conference on Industrial Electronics and Applications (ICIEA) pp. 1902 - 1908
Main Authors Wang, Zhengcai, Zhang, Ke, Yang, Zhihao, Da, Zikai, Huang, Sanao, Wang, Peizhen
Format Conference Proceeding
LanguageEnglish
Published IEEE 18.08.2023
Subjects
convolutional neural network
Image color analysis
Metals
Scattering
Statistical analysis
style transfer network
Training
Training data
Transfer learning
U-net
underwater image enhancement
Online AccessGet full text

Cover

More Information
Summary:Aiming at the problems of low contrast, dim and color distortion of underwater images caused by the attenuation and scattering of light in water propagation, an underwater image enhancement algorithm, which is based on a U-Net convolutional Neural Network is proposed. The algorithm consists of an image synthesis module and an image enhancement module. Firstly, a style transfer network based on transfer learning is built and employed to synthesize underwater images from clear images, image pairs are composed of these synthesized and original images for data expansion. Secondly, an underwater image enhancement network with a U-shaped convolutional variational autoencoder is constructed, and the image pairs serve as input to the second module for training. The qualitative and quantitative analysis results show that the proposed algorithm has good performs favorably in the color fidelity and detailed reservation of the target object.
ISSN:2158-2297
DOI:10.1109/ICIEA58696.2023.10241945