Underwater visual image denoising based on total variation method

Yangyang Li; Dahua He; Yapeng Li

doi:10.1117/12.2662724

12 April 2023 Underwater visual image denoising based on total variation method

Yangyang Li, Dahua He, Yapeng Li

Proceedings Volume 12565, Conference on Infrared, Millimeter, Terahertz Waves and Applications (IMT2022); 125652R (2023) https://doi.org/10.1117/12.2662724
Event: Conference on Infrared, Millimeter, Terahertz Waves and Applications (IMT2022), 2022, Shanghai, China

Abstract

Optical imaging technology is one of the main technology for underwater detection and recognition. However, the serious image noise occurred in the optical imaging and the signal to noise ratio of image decreased, due to water scattering and turbulence, background light interference and other factors. In this paper, an underwater visual image denoising algorithm based on total variation method is proposed to improve the signal-to-noise ratio of the underwater image at the same time keep the detail information of images. Based on the linear noise model of the image, the total variation model of the image is established and the partial differential equation of image problem is converted to optimization problems, which can be solved by gradient descent algorithm and finite difference algorithm. The method based on total variation was proposed to reduce the noise of underwater images compare with other traditional algorithms and verified by the simulation experiment and underwater experiment. Experimental verifications: after the image processing of the algorithm, the objective reference image quality evaluation index image peak signal-to-noise ratio (PSNR) was improved to more than 20 dB, and the score of no reference image quality evaluation index was improved by 4.8 times. The method can be applied to an underwater exploration and image enhancement for scatterer imaging applications.

Citation Download Citation

Yangyang Li, Dahua He, and Yapeng Li "Underwater visual image denoising based on total variation method", Proc. SPIE 12565, Conference on Infrared, Millimeter, Terahertz Waves and Applications (IMT2022), 125652R (12 April 2023); https://doi.org/10.1117/12.2662724

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