Underwater image restoration based on channel compensation and dark channel prior

Yuanchao Lou; Jianding Yu; Zhouyi Wang

doi:10.1117/12.2668558

14 February 2023 Underwater image restoration based on channel compensation and dark channel prior

Yuanchao Lou, Jianding Yu, Zhouyi Wang

Proceedings Volume 12589, International Conference on Optical Technology, Semiconductor Materials, and Devices (OTSMD 2022); 125890S (2023) https://doi.org/10.1117/12.2668558
Event: International Conference on Optical Technology, Semiconductor Materials, and Devices (OTSMD 2022), 2022, Longyan, China

Abstract

Due to the absorption and scattering of light by water medium and suspended particles, underwater images come with color deviation and blurred details. For different light absorption in different underwater environments, an adaptive compensation method for local color channels is proposed to enhance the compensation for severe attenuation areas, which is suitable for underwater scenes with multiple color deviations. The dark channel prior is used to remove the detail blurring caused by scattering, the multi-scale Gaussian convolution and gamma correction are adopted to estimate the local light, and the tolerance parameter is used to increase the transmittance of bright areas to compensate for the dark channel prior conditions. The enhanced image quality is evaluated by Underwater Image Quality Measurement (UIQM), Average Gradient (AG), and entropy. Experimental data show that the method improves the color deviation of underwater images in different environments, enhances color information, and improves the contrast of images.

Citation Download Citation

Yuanchao Lou, Jianding Yu, and Zhouyi Wang "Underwater image restoration based on channel compensation and dark channel prior", Proc. SPIE 12589, International Conference on Optical Technology, Semiconductor Materials, and Devices (OTSMD 2022), 125890S (14 February 2023); https://doi.org/10.1117/12.2668558

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available