Noise and semantic prior guided low-light image enhancement algorithm

doi:10.11772/j.issn.1001-9081.2024081187

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (9): 2966-2974.DOI: 10.11772/j.issn.1001-9081.2024081187

• Multimedia computing and computer simulation • Previous Articles

Noise and semantic prior guided low-light image enhancement algorithm

Xuejin WANG, Leilei HUANG(), Zhenhui ZHONG

School of Computer Science and Mathematics，Fujian University of Science and Technology，Fuzhou Fujian 350118，China

Received:2024-08-21 Revised:2024-10-19 Accepted:2024-10-22 Online:2024-11-07 Published:2025-09-10
Contact: Leilei HUANG
About author:WANG Xuejin， born in 1989， Ph. D.， associate professor. Her research interests include image processing， computer vision.
ZHONG Zhenhui， born in 2000， M. S. candidate. His research interests include image processing， image quality assessment.
Supported by:
Natural Science Foundation of Fujian Province(2022J01954);Education and Scientific Research Project for Middle-aged and Young Teachers of Education Department of Fujian Province(JAT210288)

噪声与语义先验引导的低照度图像增强算法

王雪津, 黄雷雷(), 钟祯辉

福建理工大学计算机科学与数学学院，福州 350118

通讯作者: 黄雷雷
作者简介:王雪津（1989—），女，福建莆田人，副教授，博士，主要研究方向：图像处理、计算机视觉
钟祯辉（2000—），男（畲族），福建福州人，硕士研究生，主要研究方向：图像处理、图像质量评价。
基金资助:
福建省自然科学基金资助项目(2022J01954);福建省自然科学基金资助项目(2023J01348);福建省教育厅中青年教师教育科研项目(JAT210288)

Abstract

Abstract:

There are non-uniform distribution characteristics of brightness， noise， and contrast in low-light images， however， the existing Low-Light Image Enhancement （LLIE） algorithms fail to fully utilize these characteristics. As a result， issues such as detail loss， color distortion， and visual discontinuity may occur， affecting the visual quality of the images. To address these problems， a noise and semantic prior guided LLIE algorithm was proposed to consider characteristics of different regions in low-light images and their semantic information adaptively. Specifically， a novel Image block Classification based Global Feature Extraction network （ICGFE） was designed to extract global features， an Information Compensation based Local Feature Extraction network （ICLFE） was introduced to extract local features， and a noise prior-guided feature fusion strategy was proposed to perform adaptive enhancement operations on image regions with different characteristics. Furthermore， a new semantic prior-guided color loss function was presented to maintain consistency of instance colors. Experimental results on the public dataset LOL （LOw-Light dataset） show that the proposed algorithm improves the Peak Signal-to-Noise Ratio （PSNR） by 1.9%-89.1% and achieves good results in Structural SIMilarity （SSIM） compared to the algorithms such as Retinex and Underexposed Photo Enhancement using Deep illumination estimation （DeepUPE）. It can be seen that the proposed algorithm can enhance image regions with different characteristics adaptively and has significant advantages in perspectives such as color restoration， detail and texture reconstruction， and noise suppression.

Key words: Low-Light Image Enhancement (LLIE), semantic prior, image block classification, noise prior, self-adaption

摘要：

低照度图像的亮度、噪声和对比度等具有非均匀分布的特性，然而现有的低照度图像增强（LLIE）算法未能充分利用这些特性，在增强过程中容易导致细节丢失、颜色失真和视觉不连贯等问题，从而影响图像的视觉质量。针对上述问题，提出噪声与语义先验引导的LLIE算法，以自适应地考虑低照度图像中不同区域的特性及其语义信息。具体来说，设计一种新的基于图像块分类的全局特征提取网络（ICGFE）提取全局特征，引入基于信息补偿的局部特征提取网络（ICLFE）提取局部特征，并提出基于噪声先验引导的特征融合策略对具有不同特性的图像区域进行自适应增强操作；此外，提出新的语义先验引导的颜色损失函数保持实例颜色的一致性。在公开数据集LOL（LOw-Light dataset）上的实验结果表明，所提算法相较于Retinex和DeepUPE（Underexposed Photo Enhancement using Deep illumination estimation）等算法，峰值信噪比（PSNR）提高了1.9%~89.1%，结构相似性（SSIM）也取得了较好的结果。可见，所提算法能自适应增强具有不同特性的图像区域，并且在颜色恢复、细节纹理还原和噪声抑制等方面均具有明显优势。

关键词: 低照度图像增强, 语义先验, 图像块分类, 噪声先验, 自适应

CLC Number:

TP391.41

Xuejin WANG, Leilei HUANG, Zhenhui ZHONG. Noise and semantic prior guided low-light image enhancement algorithm[J]. Journal of Computer Applications, 2025, 45(9): 2966-2974.

王雪津, 黄雷雷, 钟祯辉. 噪声与语义先验引导的低照度图像增强算法[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2966-2974.

Figures/Tables 11

References 51

[1]	姜雪松，姚鸿勋. 夜晚图像增强方法综述［J］. 智能计算机与应用， 2020， 10（3）： 394-403.
	JIANG X S， YAO H X. Summary of nighttime image enhancement methods ［J］. Intelligent Computer and Applications， 2020， 10（3）： 394-403.
[2]	LORE K G， AKINTAYO A， SARKAR S. LLNet： a deep auto encoder approach to natural low-light image enhancement ［J］. Pattern Recognition， 2017， 61： 650-662.
[3]	LI C， GUO C， HAN L， et al. Low-light image and video enhancement using deep learning： a survey ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2022， 44（12）： 9396-9416.
[4]	ZHENG S， MA Y， PAN J， et al. Low-light image and video enhancement： a comprehensive survey and beyond ［EB/OL］. ［2024-09-30］. .
[5]	ABDULLAH-AL-WADUD M， KABIR M H， DEWAN M A A， et al. A dynamic histogram equalization for image contrast enhancement ［J］. IEEE Transactions on Consumer Electronics， 2007， 53（2）： 593-600.
[6]	WANG S， ZHENG J， HU H M， et al. Naturalness preserved enhancement algorithm for non-uniform illumination images ［J］. IEEE Transactions on Image Processing， 2013， 22（9）： 3538-3548.
[7]	FU X， LIAO Y， ZENG D， et al. A probabilistic method for image enhancement with simultaneous illumination and reflectance estimation ［J］. IEEE Transactions on Image Processing， 2015， 24（12）： 4965-4977.
[8]	LAND E H， McCANN J J. Lightness and Retinex theory ［J］. Journal of the Optical Society of America， 1971， 61（1）： 1-11.
[9]	PARK S， YU S， MOON B， et al. Low-light image enhancement using variational optimization-based Retinex model ［J］. IEEE Transactions on Consumer Electronics， 2017， 63（2）： 178-184.
[10]	WANG X， HUANG L， CHEN H， et al. Benchmark dataset and pair-wise ranking method for quality evaluation of night-time image enhancement ［J］. IEEE Transactions on Multimedia， 2024， 26： 9436-9449.
[11]	SHI J， SHAO F， TIAN C， et al. Progressive bidirectional feature extraction and enhancement network for quality evaluation of night-time images ［J］. IEEE Transactions on Multimedia， 2024， 26： 1690-1705.
[12]	黄淑英，黎为，杨勇，等. 基于照度图引导的低照度图像增强网络［J］. 计算机辅助设计与图形学学报， 2024， 36（1）： 92-101.
	HUANG S Y， LI W， YANG Y， et al. Low-light image enhancement network guided by illuminance map ［J］. Journal of Computer-Aided Design and Computer Graphics， 2024， 36（1）： 92-101.
[13]	GUO C， LI C， GUO J， et al. Zero-reference deep curve estimation for low-light image enhancement ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 1777-1786.
[14]	YANG W， WANG S， FANG Y， et al. From fidelity to perceptual quality： a semi-supervised approach for low-light image enhancement ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 3060-3069.
[15]	牛玉贞，陈铭铭，李悦洲，等. 基于任务解耦的低照度图像增强方法［J］. 电子学报， 2024， 52（1）： 34-45.
	NIU Y Z， CHEN M M， LI Y Z， et al. Task decoupling guided low-light image enhancement ［J］. Acta Electronica Sinica， 2024， 52（1）： 34-45.
[16]	LIU R， MA L， ZHANG J， et al. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 10556-10565.
[17]	JIANG Y， GONG X， LIU D， et al. EnlightenGAN： deep light enhancement without paired supervision ［J］. IEEE Transactions on Image Processing， 2021， 30： 2340-2349.
[18]	WU W H， WENG J， ZHANG P P， et al. URetinex-Net： Retinex-based deep unfolding network for low-light image enhancement［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 5891-5900.
[19]	王瑞尧，岳雪亭，周志青，等. 最大差值图决策的低照度图像自适应增强算法［J］. 计算机应用， 2020， 40（4）： 1164-1170.
	WANG R Y， YUE X T， ZHOU Z Q， et al. Adaptive enhancement algorithm of low illumination image based on maximum difference image decision ［J］. Journal of Computer Applications， 2020， 40（4）： 1164-1170.
[20]	JIN Y， YANG W， TAN R T. Unsupervised night image enhancement： when layer decomposition meets light-effects suppression ［C］// Proceedings of the 2022 European Conference on Computer Vision， LNCS 13697. Cham： Springer， 2022： 404-421.
[21]	FU Z， YANG Y， TU X， et al. Learning a simple low-light image enhancer from paired low-light instances ［C］// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2023： 22252-22261.
[22]	FAN M， WANG W， YANG W， et al. Integrating semantic segmentation and Retinex model for low-light image enhancement［C］// Proceedings of the 2020 ACM International Conference on Multimedia. New York： ACM， 2020： 2317-2325.
[23]	ZHENG S， GUPTA G. Semantic-guided zero-shot learning for low-light image/video enhancement ［C］// Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops. Piscataway： IEEE， 2022： 581-590.
[24]	HOU Y， YANG B. Semantic attention guided low-light image enhancement with multi-scale perception ［J］. Journal of Visual Communication and Image Representation， 2024， 103： No.104242.
[25]	CHEN H， WANG Y， GUO T， et al. Pre-trained image processing Transformer ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 12294-12305.
[26]	WANG Z， CUN X， BAO J， et al. Uformer： a general U-shaped Transformer for image restoration ［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 17662-17672.
[27]	ZHANG Z， SUN W， MIN X， et al. A no-reference deep learning quality assessment method for super-resolution images based on frequency maps ［C］// Proceedings of the 2022 IEEE International Symposium on Circuits and Systems. Piscataway： IEEE， 2022： 3170-3174.
[28]	PAN Z， YUAN F， LEI J， et al. VCRNet： visual compensation restoration network for no-reference image quality assessment ［J］. IEEE Transactions on Image Processing， 2022， 31： 1613-1627.
[29]	MA K， DUANMU Z， WU Q， et al. Waterloo exploration database： new challenges for image quality assessment models ［J］. IEEE Transactions on Image Processing， 2017， 26（2）： 1004-1016.
[30]	XU B， WANG N， CHEN T， et al. Empirical evaluation of rectified activations in convolutional network ［EB/OL］. ［2024-09-30］. .
[31]	DABOV K， FOI A， KATKOVNIK V， et al. Image denoising with block-matching and 3D filtering ［C］// Proceedings of the SPIE 6064， Image Processing： Algorithms and Systems， Neural Networks， and Machine Learning. Bellingham， WA： SPIE， 2006： No.606414.
[32]	WANG J， SUN K， CHENG T， et al. Deep high-resolution representation learning for visual recognition ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2021， 43（10）： 3349-3364.
[33]	SIMONYAN K， ZISSERMAN A. Very deep convolutional networks for large-scale image recognition ［EB/OL］. ［2024-09-12］. .
[34]	WEI C， WANG W， YANG W， et al. Deep Retinex decomposition for low-light enhancement ［C］// Proceedings of the 2018 British Machine Vision Conference. Durham： BMVA Press， 2018： No.451.
[35]	YANG W， WANG W， HUANG H， et al. Sparse gradient regularized deep Retinex network for robust low-light image enhancement ［J］. IEEE Transactions on Image Processing， 2021， 30： 2072-2086.
[36]	CHEN C， CHEN Q， XU J， et al. Learning to see in the dark ［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 3291-3300.
[37]	CHEN C， CHEN Q， DO M， et al. Seeing motion in the dark ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 3184-3193.
[38]	LEE CHULWOO， LEE CHUL， KIM C S. Contrast enhancement based on layered difference representation of 2D histograms ［J］. IEEE Transactions on Image Processing， 2013， 22（12）： 5372-5384.
[39]	GUO X， LI Y， LING H. LIME： low-light image enhancement via illumination map estimation ［J］. IEEE Transactions on Image Processing， 2017， 26（2）： 982-993.
[40]	MA K， ZENG K， WANG Z. Perceptual quality assessment for multi-exposure image fusion ［J］. IEEE Transactions on Image Processing， 2015， 24（11）： 3345-3356.
[41]	YAN Z， ZHANG H， WANG B， et al. Automatic photo adjustment using deep neural networks ［J］. ACM Transactions on Graphics， 2016， 35（2）： No.11.
[42]	KINGMA D P， BA J L. Adam： a method for stochastic optimization ［EB/OL］. ［2024-09-07］. .
[43]	MITTAL A， SOUNDARARAJAN R， BOVIK A C， et al. Making a “completely blind” image quality analyzer ［J］. IEEE Signal Processing Letters， 2013， 20（3）： 209-212.
[44]	MITTAL A， MOORTHY A K， BOVIK A C. No-reference image quality assessment in the spatial domain ［J］. IEEE Transactions on Image Processing， 2012， 21（12）： 4695-4708.
[45]	ZHANG Y， ZHANG J， GUO X. Kindling the darkness： a practical low-light image enhancer ［C］// Proceedings of the 27th ACM International Conference on Multimedia. New York： ACM， 2019： 1632-1640.
[46]	WANG R， ZHANG Q， FU C W， et al. Underexposed photo enhancement using deep illumination estimation ［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 6842-6850.
[47]	ZAMIR S W， ARORA A， KHAN S， et al. Restormer： efficient Transformer for high-resolution image restoration ［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 5718-5729.
[48]	FAN C M， LIU T J， LIU K H. Half wavelet attention on M-Net+ for low-light image enhancement ［C］// Proceedings of the 2022 IEEE International Conference on Image Processing. Piscataway： IEEE， 2022： 3878-3882.
[49]	WANG C Y， BOCHKOVSKIY A， LIAO H Y M， YOLOv7： trainable bag-of-freebies sets new state-of-the-art for real-time object detectors ［C］// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2023： 7464-7475.
[50]	YANG W， YUAN Y， REN W， et al. Advancing image understanding in poor visibility environments： a collective benchmark study ［J］. IEEE Transactions on Image Processing， 2020， 29： 5737-5752.
[51]	LOH Y P， CHAN C S. Getting to know low-light images with the Exclusively Dark dataset ［J］. Computer Vision and Image Understanding， 2019， 178： 30-42.

算法	时间复杂度		LOL-v1		LOL-v2-real		LOL-v2-synthetic		SID		SMID
算法	运算量/FLOPs	Params/10⁶	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
DeepUPE^［46］	21.10	1.020	14.38	0.446	13.27	0.452	15.08	0.623	17.01	0.604	23.91	0.690
Retinex^［34］	587.47	0.840	16.75	0.550	15.46	0.562	17.13	0.798	16.48	0.578	22.83	0.684
EG^［17］	61.01	114.350	17.48	0.652	18.21	0.617	16.57	0.734	17.23	0.543	22.62	0.674
RUAS^［16］	0.85	0.003	18.23	0.721	18.37	0.723	16.55	0.652	18.44	0.581	25.88	0.744
KinD^［45］	34.99	8.020	20.87	0.799	14.74	0.641	13.29	0.578	18.02	0.583	22.18	0.634
DRBN^［14］	48.61	5.270	20.13	0.831	20.29	0.831	23.22	0.927	19.02	0.577	26.60	0.781
Restormer^［47］	144.25	26.130	22.43	0.823	19.94	0.827	21.41	0.830	22.27	0.649	26.97	0.758
IPT^［25］	6 887.00	115.310	16.27	0.504	19.80	0.813	18.30	0.811	20.53	0.561	27.03	0.783
Uformer^［26］	12.03	5.290	16.36	0.771	18.82	0.771	19.66	0.871	18.54	0.577	27.20	0.792
HWMNET^［48］	45.32	65.560	24.24	0.852	20.92	0.798	24.42	0.915	—	—	—	—
本文算法	29.59	5.320	24.71	0.843	21.93	0.845	24.85	0.916	22.77	0.619	28.92	0.802

算法	时间复杂度		LOL-v1		LOL-v2-real		LOL-v2-synthetic		SID		SMID
算法	运算量/FLOPs	Params/10⁶	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
DeepUPE^［46］	21.10	1.020	14.38	0.446	13.27	0.452	15.08	0.623	17.01	0.604	23.91	0.690
Retinex^［34］	587.47	0.840	16.75	0.550	15.46	0.562	17.13	0.798	16.48	0.578	22.83	0.684
EG^［17］	61.01	114.350	17.48	0.652	18.21	0.617	16.57	0.734	17.23	0.543	22.62	0.674
RUAS^［16］	0.85	0.003	18.23	0.721	18.37	0.723	16.55	0.652	18.44	0.581	25.88	0.744
KinD^［45］	34.99	8.020	20.87	0.799	14.74	0.641	13.29	0.578	18.02	0.583	22.18	0.634
DRBN^［14］	48.61	5.270	20.13	0.831	20.29	0.831	23.22	0.927	19.02	0.577	26.60	0.781
Restormer^［47］	144.25	26.130	22.43	0.823	19.94	0.827	21.41	0.830	22.27	0.649	26.97	0.758
IPT^［25］	6 887.00	115.310	16.27	0.504	19.80	0.813	18.30	0.811	20.53	0.561	27.03	0.783
Uformer^［26］	12.03	5.290	16.36	0.771	18.82	0.771	19.66	0.871	18.54	0.577	27.20	0.792
HWMNET^［48］	45.32	65.560	24.24	0.852	20.92	0.798	24.42	0.915	—	—	—	—
本文算法	29.59	5.320	24.71	0.843	21.93	0.845	24.85	0.916	22.77	0.619	28.92	0.802

算法	DICM		LIME		MEF		NPE
算法	BRISQUE	NIQE	BRISQUE	NIQE	BRISQUE	NIQE	BRISQUE	NIQE
Zero-DCE^［13］	27.56	4.58	20.44	5.82	17.32	4.93	20.72	4.53
KinD^［45］	48.72	5.15	39.91	5.03	49.94	5.47	36.85	4.98
RUAS^［16］	39.75	5.25	27.59	4.26	23.68	3.83	47.85	5.53
PairLIE^［21］	33.31	4.03	25.32	4.58	27.53	4.06	28.27	4.18
HWMNET^［48］	35.34	4.75	26.46	5.07	28.56	4.32	32.68	4.25
本文算法	32.12	4.32	23.82	4.18	25.59	4.15	27.63	4.09

算法	DICM		LIME		MEF		NPE
算法	BRISQUE	NIQE	BRISQUE	NIQE	BRISQUE	NIQE	BRISQUE	NIQE
Zero-DCE^［13］	27.56	4.58	20.44	5.82	17.32	4.93	20.72	4.53
KinD^［45］	48.72	5.15	39.91	5.03	49.94	5.47	36.85	4.98
RUAS^［16］	39.75	5.25	27.59	4.26	23.68	3.83	47.85	5.53
PairLIE^［21］	33.31	4.03	25.32	4.58	27.53	4.06	28.27	4.18
HWMNET^［48］	35.34	4.75	26.46	5.07	28.56	4.32	32.68	4.25
本文算法	32.12	4.32	23.82	4.18	25.59	4.15	27.63	4.09

消融模块	LOL-v1		LOL-v2-real		LOL-v2-synthetic		SID		SMID
消融模块	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
W/O ICGFE	18.95	0.775	18.15	0.724	21.09	0.873	20.04	0.582	23.33	0.712
W/O ICLFE	23.86	0.825	19.17	0.785	23.67	0.919	22.03	0.601	26.42	0.755
W/O Lcolor	24.52	0.842	21.38	0.841	24.23	0.921	22.55	0.629	28.19	0.807
W/O NPIC	22.09	0.823	19.52	0.756	21.98	0.892	21.01	0.595	27.99	0.792
本文算法	24.71	0.843	21.93	0.845	24.85	0.916	22.77	0.619	28.92	0.802

Noise and semantic prior guided low-light image enhancement algorithm

噪声与语义先验引导的低照度图像增强算法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 51

Related Articles 15

Recommended Articles

Metrics

算法	AP@0.5	AP@0.5：0.95
Zero-DCE^［13］	72.22	33.32
EG^［17］	70.21	32.02
RUAS^［16］	71.57	32.62
DRBN^［14］	68.35	30.89
KinD^［43］	70.14	32.19
Restormer^［45］	71.45	33.02
PairLIE^［21］	68.13	30.85
HWMNET^［46］	71.32	32.98
本文算法	72.61	33.72

算法	Bicycle	Boat	Bottle	bus	Car	Cat	Chair	Cup	Dog	Motor	People	Table	Mean
YOLOv7+Zero-DCE^［13］	75.8	66.5	66.4	84.9	77.2	56.3	53.8	59.1	63.5	64.1	68.3	46.3	65.2
YOLOv7+EG^［17］	70.6	64.5	67.1	83.6	76.8	53.7	58.9	57.9	62.2	59.1	69.2	43.5	63.9
YOLOv7+RUAS^［16］	72.1	62.3	66.3	75.4	77.1	55.9	60.9	61.5	60.2	61.5	69.4	46.8	64.1
YOLOv7+DRBN^［14］	69.8	65.3	62.9	82.5	73.1	50.8	57.3	55.1	61.3	58.8	67.7	40.9	62.1
YOLOv7+KinD^［45］	72.3	66.2	58.8	83.2	74.2	55.3	61.9	61.2	62.9	63.1	69.7	45.3	64.5
YOLOv7+Restormer^［47］	76.3	65.2	63.9	83.6	75.5	56.8	54.8	58.3	64.3	62.9	67.3	43.8	64.3
YOLOv7+PairLIE^［21］	73.5	63.9	66.1	84.8	78.3	54.8	60.3	55.9	61.6	60.8	68.2	42.6	64.2
YOLOv7+HWMNET^［48］	75.6	64.4	65.2	79.9	76.5	55.3	52.9	57.6	61.8	62.3	68.9	43.2	63.6
YOLOv7+本文算法	76.1	67.2	63.9	85.9	76.9	57.5	56.9	59.3	66.2	64.8	69.5	44.1	65.7

[1]	Ying HUANG, Shengmei GAO, Guang CHEN, Su LIU. Low-light image enhancement network combining signal-to-noise ratio guided dual-branch structure and histogram equalization [J]. Journal of Computer Applications, 2025, 45(6): 1971-1979.
[2]	Mengyuan HUANG, Kan CHANG, Mingyang LING, Xinjie WEI, Tuanfa QIN. Progressive enhancement algorithm for low-light images based on layer guidance [J]. Journal of Computer Applications, 2024, 44(6): 1911-1919.
[3]	ZHANG Susu, NI Jiancheng, ZHOU Zili, HOU Jie. Image generation based on semantic labels and noise prior [J]. Journal of Computer Applications, 2020, 40(5): 1431-1439.
[4]	PEI Pei, LI Caiwei, LYU Bote. Improved migration operator biogeography-based optimization algorithm and its application in PID parameter tuning [J]. Journal of Computer Applications, 2020, 40(3): 728-734.
[5]	ZHU Jie, ZHANG Wenyi, XUE Fei. Storage location assignment optimization of stereoscopic warehouse based on genetic simulated annealing algorithm [J]. Journal of Computer Applications, 2020, 40(1): 284-291.
[6]	JIN Tao, DONG Xiucheng, LI Yining, REN Lei, FAN Peipei. Optimization of fractional PID controller parameters based on improved PSO algorithm [J]. Journal of Computer Applications, 2019, 39(3): 796-801.
[7]	KONG Yazhou, ZHANG Liancheng, WANG Zhenxing. Address hopping proactive defense model in IPv6 based on sliding time window [J]. Journal of Computer Applications, 2018, 38(7): 1936-1940.
[8]	CHEN Ping, GONG Xun. Face alignment method based on scale self-adaption and incremental learning [J]. Journal of Computer Applications, 2018, 38(7): 2064-2069.
[9]	QIAN Tanghui, LUO Zhiqing, LI Guojia, LI Yingyun, LI Xiankai. Scale adaptive improvement of kernel correlation filter tracking algorithm [J]. Journal of Computer Applications, 2017, 37(3): 811-816.
[10]	WANG Haijun, LI Jiaxun, ZHAO Haitao, WANG Shan. Anti-jamming network architecture self-adaption technology based on cooperation and cognition [J]. Journal of Computer Applications, 2016, 36(9): 2367-2373.
[11]	DONG Yuehua, LIU Li. Data discretization algorithm based on adaptive improved particle swarm optimization [J]. Journal of Computer Applications, 2016, 36(1): 188-193.
[12]	CHEN Xianyi, ZHAO Liping, CHEN Zhizhong, LIN Tao. 2D intra string copy for screen content coding [J]. Journal of Computer Applications, 2015, 35(9): 2640-2647.
[13]	LONG Peng, LU Huaxiang. Weighted guided image filtering algorithm using Laplacian-of-Gaussian edge detector [J]. Journal of Computer Applications, 2015, 35(9): 2661-2665.
[14]	QIAO Ying, HE Yucheng, ZHOU Lin. Novel channel-adaptive coded cooperation scheme [J]. Journal of Computer Applications, 2015, 35(5): 1218-1223.
[15]	LI Guoliang, WEI Zhenhua, XU Lei. Improved artificial bee colony algorithm using phased search [J]. Journal of Computer Applications, 2015, 35(4): 1057-1061.