Low illumination image enhancement based on retinex theory

Lan Zhao; Youqian Guo

doi:10.1117/12.3005820

10 October 2023 Low illumination image enhancement based on retinex theory

Lan Zhao, Youqian Guo

Proceedings Volume 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023); 127995E (2023) https://doi.org/10.1117/12.3005820
Event: 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 2023, Kuala Lumpur, Malaysia

Abstract

Aiming at the problem that low visible light and noise will not only reduce the visual beauty of images but also cause the loss of important information, an improved Retinex theory method is put forward to enhance low illumination images. More specifically, a light analytic model is applied before the original low illumination image to refine the original illumination image and construct an image with good parameters. Finally, color recovery factor is added to readjust the color distortion caused by contrast enhancement in local region of the image, so as to realize the corresponding image enhancement. Experiments on some challenging real-world low-light images revealed the effectiveness of our limiting images, and shows its better than SSR (Single Scale Retinex) and MSR (Multi–scale Retinex) and MSRCR (such as Multi– scale Retinex with Color Restoration) technology.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Lan Zhao and Youqian Guo "Low illumination image enhancement based on retinex theory", Proc. SPIE 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 127995E (10 October 2023); https://doi.org/10.1117/12.3005820

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