Multi-Purpose Oriented Real-World Underwater Image Enhancement

Zetian Mi,Xianping Fu,Yuanyuan Li,Yafei Wang

doi:10.1109/access.2020.3002883

Zetian Mi, Xianping Fu + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.3002883

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 16	License type: CC BY 4.0

Affiliation: Dalian Maritime University, Peng Cheng Laboratory

Abstract

Images captured underwater usually suffer from weak illumination, color cast, fuzz and noise, which severely degrade the visibility. Numerous methods have been proposed to improve the quality of underwater images, but rarely of them can give a comprehensive consideration to all these problems, which makes them hard to adapt for various and complex real-world underwater scenes. Herein, a novel multi-purpose oriented approach for real-world underwater image enhancement is proposed. To manipulate different information on the corresponding layers, we firstly decompose the input image into illumination layer and reflectance layer. Subsequently, compensation of the brightness is carried out on the illumination layer, while color correction and contrast enhancement are implemented on the reflectance layer through a multi-scale processing strategy. Benefiting from this strategy, the proposed approach is provided with high control flexibility, which can significantly improve the visibility of underwater images while efficiently suppress the amplification of noise. Both qualitative and quantitative evaluations demonstrate that the proposed method has superior robustness, accuracy and effectiveness for complex marine circumstance.

Highlights

Due to the shortage of resources on land, undersea world has obtained considerable attention
Color correction is applied on the base layer b of the reflectance, while contrast enhancement is applied in the gradient domain of detail layers di in order to avoid the generation of artifacts
In order to significantly improve the structure and details of interest while avoid artifacts, the contrast of the underwater image is enhanced by manipulating the gradient domain of the reflectance, rather than solving the image formation model (IFM)

Summary

INTRODUCTION

Due to the shortage of resources on land, undersea world has obtained considerable attention. In order to adapt to both low illumination image and underwater image, Dai et al [6] employs different strategies on the incident light and improves the contrast of the reflectance These enhancing-based methods do not consider the physical properties of underwater imaging mechanism, so that the results tend to bring out artifacts, over-enhancement or color distortion. To dealing with the low-light deep-sea circumstance, Li et al [24] proposes an adaptive bright-color channel based low-light underwater enhancement method followed by a denoising and a color correction method to enhance such images and remove noise and artifacts. THE PROPOSED METHOD a multi-purpose oriented approach is proposed to enhance real-world underwater images, which can restore the brightness, color and contrast simultaneously.

MULTI-SCALE DECOMPOSITION OF THE REFLECTANCE

POST PROCESSING

EXPERIMENTAL RESULTS AND DISCUSSION

CONCLUSION