Multi-feature Learning Adaptive Network for Underwater Image Enhancement

Qingzheng Wang

North China University of Water Resources and Electric Power, School of Information Engineering, China.

Bin Li *

North China University of Water Resources and Electric Power, School of Information Engineering, China.

Xixi Zhu

North China University of Water Resources and Electric Power, School of Information Engineering, China.

*Author to whom correspondence should be addressed.


Abstract

Underwater image enhancement faces variety of challenges owing to the diversity of underwater scenes (viewed as water types) and the rich multi-frequency information. To deal with these challenges, this paper proposes a multi-feature learning adaptive underwater image enhancement network comprising an adaptive module and a dual-layer synchronous enhancement network. First, we design an adaptive module which enables the determination of water type inside the model and eliminates the negative effect of water type diversity by building water type related features. Then, the model learns high-frequency and low-frequency features through a dual-layer synchronous enhancement network to extract more comprehensive information. Finally, the outputs of the dual-layer network are merged to obtain more realistic underwater enhanced images. Numerous experiments have shown that the proposed method outperforms the comparison method for visual perception and assessment metrics.

Keywords: Underwater image, image enhancement, deep learning, multi-frequency information


How to Cite

Wang, Qingzheng, Bin Li, and Xixi Zhu. 2024. “Multi-Feature Learning Adaptive Network for Underwater Image Enhancement”. Journal of Engineering Research and Reports 26 (5):66-75. https://doi.org/10.9734/jerr/2024/v26i51135.

Downloads

Download data is not yet available.