Deep Learning-Based Low-Light Imaging Considering Image Signal Processing (Image Signal Processing을 고려한 딥러닝 기반 저조도 이미지 처리)

Minsu Kwon (권민수)

doi:10.9708/jksci.2023.28.02.019

Deep Learning-Based Low-Light Imaging Considering Image Signal Processing

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2023, 28(2), pp.19-25
DOI : 10.9708/jksci.2023.28.02.019
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : January 2, 2023
Accepted : February 9, 2023
Published : February 28, 2023

Minsu Kwon ¹

¹에너자이

Accredited

ABSTRACT

In this paper, we propose a method for improving raw images captured in a low light condition based on deep learning considering the image signal processing. In the case of a smart phone camera, compared to a DSLR camera, the size of a lens or sensor is limited, so the noise increases and the reduces the quality of images in low light conditions. Existing deep learning-based low-light image processing methods create unnatural images in some cases since they do not consider the lens shading effect and white balance, which are major factors in the image signal processing. In this paper, pixel distances from the image center and channel average values are used to consider the lens shading effect and white balance with a deep learning model. Experiments with low-light images taken with a smart phone demonstrate that the proposed method achieves a higher peak signal to noise ratio and structural similarity index measure than the existing method by creating high-quality low-light images.

KEYWORDS

Low Light, Image Sensor, Deep Learning, Smart Phone, Camera

Citation status

* References for papers published after 2023 are currently being built.

[confproc] Abdelhamed, A. / 2018 / A high-quality denoising dataset for smartphone cameras / Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition : 1692~1700

[confproc] Cepeda-Negrete, J / 2014 / Gray-world assumption on perceptual color spaces / Pacific-Rim Symposium on Image and Video Technology : 493~504

[confproc] Chen, C / 2018 / Learning to see in the dark / Proceedings of the IEEE conference on computer vision and pattern recognition : 3291~3300

[confproc] Guo, C. / 2020 / Zero-reference deep curve estimation for low-light image enhancement / Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 1780~1789

[confproc] Ignatov, A. / 2021 / Fast camera image denoising on mobile gpus with deep learning, mobile ai 2021 challenge: Report / Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 2515~2524

[confproc] Lim, B / 2017 / Enhanced deep residual networks for single image super-resolution / Proceedings of the IEEE conference on computer vision and pattern recognition workshops : 136~144

[confproc] Lugmayr, A / 2020 / Srflow:Learning the super-resolution space with normalizing flow / European conference on computer vision / Springer : 715~732

[confproc] Ronneberger, O. / 2015 / U-net:Convolutional networks for biomedical image segmentation / International Conference on Medical image computing and computer-assisted intervention / Springer, Cham : 234~241

[journal] Z. Wang / 2004 / Image Quality Assessment: From Error Visibility to Structural Similarity / IEEE Transactions on Image Processing / Institute of Electrical and Electronics Engineers (IEEE) 13(4) : 600~612

[journal] Ian T. Young / 2000 / Shading Correction: Compensation for Illumination and Sensor Inhomogeneities / Current Protocols in Cytometry / Wiley 14(1)

[confproc] Zhang, Y. / 2018 / Image super-resolution using very deep residual channel attention networks / Proceedings of the European conference on computer vision (ECCV) : 286~301

This paper was written with support from the National Research Foundation of Korea.

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Deep Learning-Based Low-Light Imaging Considering Image Signal Processing

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Deep Learning-Based Low-Light Imaging Considering Image Signal Processing

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (11) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.