Low-light image enhancement based on deep convolutional neural networks

Yong Chen; Dong Chen

doi:10.1117/12.2600383

1 June 2021 Low-light image enhancement based on deep convolutional neural networks

Yong Chen, Dong Chen

Proceedings Volume 11848, International Conference on Signal Image Processing and Communication (ICSIPC 2021); 118480G (2021) https://doi.org/10.1117/12.2600383
Event: International Conference on Signal Image Processing and Communication (ICSIPC 2021), 2021, Chengdu, China

Abstract

A reference-free low-illumination image enhancement method based on deep convolutional neural networks is proposed to address the problem that low-illumination image enhancement algorithms do not take into account noise suppression while achieving detail enhancement. First, the illumination and reflection components are extracted from the input lowillumination image based on Retinex theory, and optimised separately, and then the optimised illumination and reflection components are multiplied to obtain the enhanced image. loss to update the network parameters. The experimental results show that our algorithm can effectively enhance the contrast and brightness of low-illumination images compared to existing mainstream algorithms, while maintaining the naturalness of the images.

Citation Download Citation

Yong Chen and Dong Chen "Low-light image enhancement based on deep convolutional neural networks", Proc. SPIE 11848, International Conference on Signal Image Processing and Communication (ICSIPC 2021), 118480G (1 June 2021); https://doi.org/10.1117/12.2600383

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