In order to solve the low-quality problems such as low brightness, poor contrast, noise interference and color imbalance in night images, a night image enhancement algorithm based on MDIFE-Net curve estimation is presented. This algorithm mainly consists of three parts: Firstly, we design an illumination estimation curve (IEC), which adjusts the pixel level of the low illumination image domain through a non-linear fitting function, maps to the enhanced image domain, and effectively eliminates the effect of illumination loss; Secondly, the DCE-Net is improved, replacing the original Relu activation function with a smoother Mish activation function, so that the parameters can be better updated; Finally, illumination estimation loss function, which combines image attributes with fidelity, is designed to drive the no-reference image enhancement, which preserves more image details while enhancing the night image. The experimental results show that our method can not only effectively improve the image contrast, but also make the details of the target more prominent, improve the visual quality of the image, and make the image achieve a better visual effect. Compared with four existing low illumination image enhancement algorithms, the NIQE and STD evaluation index values are better than other representative algorithms, verify the feasibility and validity of the algorithm, and verify the rationality and necessity of each component design through ablation experiments.
Jing ZHANG
Xi'an University of Science and Technology,Northwest University
Dan LI
Xi'an University of Science and Technology
Hong-an LI
Xi'an University of Science and Technology
Xuewen LI
Xi'an University of Science and Technology
Lizhi ZHANG
Xi'an Xike Safety Technology, Co., Ltd.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Jing ZHANG, Dan LI, Hong-an LI, Xuewen LI, Lizhi ZHANG, "A Night Image Enhancement Algorithm Based on MDIFE-Net Curve Estimation" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 2, pp. 229-239, February 2023, doi: 10.1587/transinf.2022EDP7121.
Abstract: In order to solve the low-quality problems such as low brightness, poor contrast, noise interference and color imbalance in night images, a night image enhancement algorithm based on MDIFE-Net curve estimation is presented. This algorithm mainly consists of three parts: Firstly, we design an illumination estimation curve (IEC), which adjusts the pixel level of the low illumination image domain through a non-linear fitting function, maps to the enhanced image domain, and effectively eliminates the effect of illumination loss; Secondly, the DCE-Net is improved, replacing the original Relu activation function with a smoother Mish activation function, so that the parameters can be better updated; Finally, illumination estimation loss function, which combines image attributes with fidelity, is designed to drive the no-reference image enhancement, which preserves more image details while enhancing the night image. The experimental results show that our method can not only effectively improve the image contrast, but also make the details of the target more prominent, improve the visual quality of the image, and make the image achieve a better visual effect. Compared with four existing low illumination image enhancement algorithms, the NIQE and STD evaluation index values are better than other representative algorithms, verify the feasibility and validity of the algorithm, and verify the rationality and necessity of each component design through ablation experiments.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7121/_p
Copy
@ARTICLE{e106-d_2_229,
author={Jing ZHANG, Dan LI, Hong-an LI, Xuewen LI, Lizhi ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Night Image Enhancement Algorithm Based on MDIFE-Net Curve Estimation},
year={2023},
volume={E106-D},
number={2},
pages={229-239},
abstract={In order to solve the low-quality problems such as low brightness, poor contrast, noise interference and color imbalance in night images, a night image enhancement algorithm based on MDIFE-Net curve estimation is presented. This algorithm mainly consists of three parts: Firstly, we design an illumination estimation curve (IEC), which adjusts the pixel level of the low illumination image domain through a non-linear fitting function, maps to the enhanced image domain, and effectively eliminates the effect of illumination loss; Secondly, the DCE-Net is improved, replacing the original Relu activation function with a smoother Mish activation function, so that the parameters can be better updated; Finally, illumination estimation loss function, which combines image attributes with fidelity, is designed to drive the no-reference image enhancement, which preserves more image details while enhancing the night image. The experimental results show that our method can not only effectively improve the image contrast, but also make the details of the target more prominent, improve the visual quality of the image, and make the image achieve a better visual effect. Compared with four existing low illumination image enhancement algorithms, the NIQE and STD evaluation index values are better than other representative algorithms, verify the feasibility and validity of the algorithm, and verify the rationality and necessity of each component design through ablation experiments.},
keywords={},
doi={10.1587/transinf.2022EDP7121},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - A Night Image Enhancement Algorithm Based on MDIFE-Net Curve Estimation
T2 - IEICE TRANSACTIONS on Information
SP - 229
EP - 239
AU - Jing ZHANG
AU - Dan LI
AU - Hong-an LI
AU - Xuewen LI
AU - Lizhi ZHANG
PY - 2023
DO - 10.1587/transinf.2022EDP7121
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2023
AB - In order to solve the low-quality problems such as low brightness, poor contrast, noise interference and color imbalance in night images, a night image enhancement algorithm based on MDIFE-Net curve estimation is presented. This algorithm mainly consists of three parts: Firstly, we design an illumination estimation curve (IEC), which adjusts the pixel level of the low illumination image domain through a non-linear fitting function, maps to the enhanced image domain, and effectively eliminates the effect of illumination loss; Secondly, the DCE-Net is improved, replacing the original Relu activation function with a smoother Mish activation function, so that the parameters can be better updated; Finally, illumination estimation loss function, which combines image attributes with fidelity, is designed to drive the no-reference image enhancement, which preserves more image details while enhancing the night image. The experimental results show that our method can not only effectively improve the image contrast, but also make the details of the target more prominent, improve the visual quality of the image, and make the image achieve a better visual effect. Compared with four existing low illumination image enhancement algorithms, the NIQE and STD evaluation index values are better than other representative algorithms, verify the feasibility and validity of the algorithm, and verify the rationality and necessity of each component design through ablation experiments.
ER -