Dynamic dictionary learning based spatio-spectral fusion for noisy hyper-spectral images

doi:10.11772/j.issn.1001-9081.2025040411

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (9): 2941-2948.DOI: 10.11772/j.issn.1001-9081.2025040411

• Multimedia computing and computer simulation • Previous Articles

Dynamic dictionary learning based spatio-spectral fusion for noisy hyper-spectral images

Jing YANG¹^,², Jianbin ZHAO¹, Lu CHEN³(), Haotian CHI¹, Tao YAN³, Bin CHEN⁴^,⁵

^1.School of Automation and Software Engineering，Shanxi University，Taiyuan Shanxi 030031，China
^2.Technology Department，Taiyuan Satellite Launch Center，Taiyuan Shanxi 030027，China
^3.Institute of Big Data Science and Industry，Shanxi University，Taiyuan Shanxi 030006，China
^4.Chongqing Research Institute，Harbin Institute of Technology，Chongqing 401151，China
^5.International Institute for Artificial Intelligence，Harbin Institute of Technology （Shenzhen），Shenzhen Guangdong 518055，China

Received:2025-04-17 Revised:2025-06-05 Accepted:2025-06-10 Online:2025-06-13 Published:2025-09-10
Contact: Lu CHEN
About author:YANG Jing， born in 1990， Ph. D.， lecturer. Her research interests include hyper-spectral image processing， spatio-spectral fusion.
ZHAO Jianbin， born in 2001， M. S. candidate. His research interests include hyper-spectral image processing.
CHI Haotian， born in 1990， Ph. D.， lecturer. His research interests include information security.
YAN Tao， born in 1987， Ph. D.， associate professor. His research interests include 3D reconstruction.
CHEN Bin， born in 1970， Ph. D.， professor. His research interests include machine vision.
Supported by:
National Natural Science Foundation of China(62406181);Scientific Research Project for Returned Overseas Students in Shanxi Province(2023-023);Fundamental Research Program of Shanxi Province(202203021222010)

基于动态字典学习的含噪高光谱图像空谱融合

杨静¹^,², 赵建斌¹, 陈路³(), 池浩田¹, 闫涛³, 陈斌⁴^,⁵

^1.山西大学自动化与软件学院，太原 030031
^2.太原卫星发射中心技术部，太原 030027
^3.山西大学大数据科学与产业研究院，太原 030006
^4.哈尔滨工业大学重庆研究院，重庆 401151
^5.哈尔滨工业大学（深圳）国际人工智能研究院，广东深圳 518055

通讯作者: 陈路
作者简介:杨静（1990—），女，河北故城人，讲师，博士，主要研究方向：高光谱图像处理、空谱融合
赵建斌（2001—），男，山西平遥人，硕士研究生，主要研究方向：高光谱图像处理
池浩田（1990—），男，山西长治人，讲师，博士，主要研究方向：信息安全
闫涛（1987—），男，山西定襄人，副教授，博士，CCF会员，主要研究方向：三维重建
陈斌（1970—），男，四川广汉人，教授，博士，主要研究方向：机器视觉。
基金资助:
国家自然科学基金资助项目(62406181);国家自然科学基金资助项目(62373233);山西省回国留学人员科研项目(2023-023);山西省基础研究计划项目(202203021222010);山西省基础研究计划项目(202203021222005)

Abstract

Abstract:

Traditional Hyper-Spectral Image （HSI） spatio-spectral fusion algorithms usually use static spectral dictionary， in which the dictionary learning and the image fusion are two separate processes， thereby giving poor performance when processing noisy spatio-spectral fusion tasks. To address this problem， a noisy HSI spatio-spectral fusion algorithm based on Dynamic Dictionary Learning （DDL） was proposed， which adopted an iterative strategy that updates dictionary atoms dynamically during the fusion process， thereby collaborating to complete the spatio-spectral fusion and noise removal tasks. Firstly， a coarse denoising was performed on the input HSI and the denoising result was utilized to initialize the spectral dictionary. Secondly， the sparse representation technique was employed to fuse the two input images with the above initialized dictionary， resulting an intermediate fusion image. Thirdly， the intermediate fusion image was fed back to the dictionary learning module to update the dictionary atoms continuously， thereby forming a dynamic spectral dictionary. Finally， by iterating the above process， the final output image was obtained. Simulation results on three remote sensing HSI datasets show that the proposed algorithm can remove noise effectively while improving spatial resolution of the images. At the same time， experimental results on real noisy image bands indicate that the proposed algorithm can improve visual quality of the fused images effectively. On Cuprite Mine dataset， the Peak Signal-to-Noise Ratio （PSNR） of the proposed algorithm is increased by 32.48% and 10.72% respectively compared to those of Generalized Tensor Nuclear Norm （GTNN） method and AL-NSSR method — the method of denoising first and then fusion， with Gaussian noise variance of 0.15 and amplification factor of 8.

Key words: Hyper-Spectral Image (HSI), spatio-spectral fusion, noise, spectral dictionary learning, iterative sparse representation

摘要：

针对传统高光谱图像（HSI）空谱融合算法通常采用静态光谱字典，而字典学习与图像融合过程相分离，对含有噪声的空谱融合任务处理效果不佳的问题，提出一种基于动态字典学习（DDL）的含噪HSI空谱融合算法。该算法采用迭代思想，在融合过程中动态更新字典原子，从而协作完成空谱融合及噪声去除任务。首先，对输入的HSI进行粗去噪，并利用去噪结果初始化光谱字典；其次，利用上述初始化字典对两幅待融合图像进行稀疏表示，以得到中间融合结果；再次，将中间融合结果反馈给字典学习模块，不断更新字典原子，构造动态光谱字典；最后，通过迭代以上过程得到最终的输出图像。在3个遥感HSI数据集上的仿真实验结果表明，所提算法能够在提升图像空间分辨率的同时有效去除噪声。同时，在真实含噪图像波段上的实验结果表明，所提算法能够有效提高融合图像的视觉质量。在Cuprite Mine数据集上，在高斯噪声方差为0.15且放大倍数为8时，与基于广义张量核范数（GTNN）的方法和先去噪后融合的方法AL-NSSR方法相比，所提算法的峰值信噪比（PSNR）分别提升了32.48%和10.72%。

关键词: 高光谱图像, 空谱融合, 噪声, 光谱字典学习, 迭代稀疏表示

CLC Number:

TP751

Jing YANG, Jianbin ZHAO, Lu CHEN, Haotian CHI, Tao YAN, Bin CHEN. Dynamic dictionary learning based spatio-spectral fusion for noisy hyper-spectral images[J]. Journal of Computer Applications, 2025, 45(9): 2941-2948.

杨静, 赵建斌, 陈路, 池浩田, 闫涛, 陈斌. 基于动态字典学习的含噪高光谱图像空谱融合[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2941-2948.

Figures/Tables 8

Fig. 1 Comparison between static dictionary and dynamic dictionary

Fig. 2 Flow of proposed DDL algorithm

Tab. 1 Comparison of experimental results of different spatio-spectral fusion algorithms with magnification factor of 8

图像	算法	$σ = 0.1$ 0				$σ = 0.12$				$σ = 0.15$
图像	算法	RMSE	PSNR/dB	SAM/（°）	ERGAS	RMSE	PSNR/dB	SAM/（°）	ERGAS	RMSE	PSNR/dB	SAM/（°）	ERGAS
Pavia Center	HSSF	7.70	30.40	9.24	2.49	9.05	28.99	10.59	2.88	11.03	27.28	12.65	3.45
	GTNN	9.27	28.78	12.06	3.01	10.88	27.40	13.82	3.49	13.25	25.68	16.24	4.19
	NSSR-AL	4.29	35.49	4.92	1.46	4.73	34.63	5.32	1.59	5.66	33.07	6.22	1.88
	AL-NSSR	3.78	36.59	4.88	1.36	4.23	35.60	5.43	1.53	5.35	33.56	6.69	1.90
	DDL	3.64	36.90	4.66	1.32	3.71	36.74	4.65	1.32	4.27	35.51	5.29	1.51
Pavia University	HSSF	8.43	29.61	8.66	2.59	10.46	27.74	10.71	3.21	11.59	26.85	11.55	3.48
	GTNN	11.41	26.98	12.49	3.36	12.58	26.14	13.69	3.71	14.34	25.00	15.41	4.22
	NSSR-AL	4.30	35.45	4.37	1.35	6.02	32.54	5.90	1.85	5.52	33.29	5.39	1.73
	AL-NSSR	3.62	36.95	4.10	1.17	3.95	36.19	4.40	1.28	4.68	34.72	5.19	1.52
	DDL	3.55	37.11	3.96	1.16	3.77	36.59	4.12	1.23	4.14	35.79	4.45	1.34
Cuprite Mine	HSSF	7.54	30.58	6.94	13.60	8.02	30.04	6.84	14.37	8.17	29.89	6.59	13.41
	GTNN	7.49	30.63	6.83	10.91	9.04	29.00	8.14	13.03	11.31	27.06	9.96	16.18
	NSSR-AL	3.46	37.33	3.13	4.56	3.87	36.37	3.47	5.61	4.69	34.71	4.17	7.16
	AL-NSSR	4.40	35.26	4.09	5.65	4.85	34.40	4.52	6.78	6.13	32.38	5.69	8.63
	DDL	2.91	38.85	2.75	3.29	3.50	37.24	3.27	4.20	4.11	35.85	3.84	5.08

Tab. 1 Comparison of experimental results of different spatio-spectral fusion algorithms with magnification factor of 8

图像	算法	$σ = 0.1$ 0				$σ = 0.12$				$σ = 0.15$
图像	算法	RMSE	PSNR/dB	SAM/（°）	ERGAS	RMSE	PSNR/dB	SAM/（°）	ERGAS	RMSE	PSNR/dB	SAM/（°）	ERGAS
Pavia Center	HSSF	7.70	30.40	9.24	2.49	9.05	28.99	10.59	2.88	11.03	27.28	12.65	3.45
	GTNN	9.27	28.78	12.06	3.01	10.88	27.40	13.82	3.49	13.25	25.68	16.24	4.19
	NSSR-AL	4.29	35.49	4.92	1.46	4.73	34.63	5.32	1.59	5.66	33.07	6.22	1.88
	AL-NSSR	3.78	36.59	4.88	1.36	4.23	35.60	5.43	1.53	5.35	33.56	6.69	1.90
	DDL	3.64	36.90	4.66	1.32	3.71	36.74	4.65	1.32	4.27	35.51	5.29	1.51
Pavia University	HSSF	8.43	29.61	8.66	2.59	10.46	27.74	10.71	3.21	11.59	26.85	11.55	3.48
	GTNN	11.41	26.98	12.49	3.36	12.58	26.14	13.69	3.71	14.34	25.00	15.41	4.22
	NSSR-AL	4.30	35.45	4.37	1.35	6.02	32.54	5.90	1.85	5.52	33.29	5.39	1.73
	AL-NSSR	3.62	36.95	4.10	1.17	3.95	36.19	4.40	1.28	4.68	34.72	5.19	1.52
	DDL	3.55	37.11	3.96	1.16	3.77	36.59	4.12	1.23	4.14	35.79	4.45	1.34
Cuprite Mine	HSSF	7.54	30.58	6.94	13.60	8.02	30.04	6.84	14.37	8.17	29.89	6.59	13.41
	GTNN	7.49	30.63	6.83	10.91	9.04	29.00	8.14	13.03	11.31	27.06	9.96	16.18
	NSSR-AL	3.46	37.33	3.13	4.56	3.87	36.37	3.47	5.61	4.69	34.71	4.17	7.16
	AL-NSSR	4.40	35.26	4.09	5.65	4.85	34.40	4.52	6.78	6.13	32.38	5.69	8.63
	DDL	2.91	38.85	2.75	3.29	3.50	37.24	3.27	4.20	4.11	35.85	3.84	5.08

Tab. 2 Comparison of experimental results of different spatio-spectral fusion algorithms with magnification factor of 16

图像	算法	$σ = 0.1$ 0				$σ = 0.12$				$σ = 0.15$
图像	算法	RMSE	PSNR/dB	SAM/（°）	ERGAS	RMSE	PSNR/dB	SAM/（°）	ERGAS	RMSE	PSNR/dB	SAM/（°）	ERGAS
Pavia Center	HSSF	10.09	28.05	11.22	1.69	10.60	27.62	12.01	1.80	11.49	26.92	12.83	1.90
	GTNN	10.24	27.92	12.19	1.62	11.61	26.84	13.51	1.83	14.06	25.17	15.66	2.21
	NSSR-AL	5.58	33.18	6.32	0.92	6.40	32.01	7.23	1.06	6.96	31.27	7.85	1.13
	AL-NSSR	5.53	33.28	6.73	0.98	8.02	30.05	9.15	1.43	9.09	28.96	10.61	1.62
	DDL	5.12	33.94	6.16	0.92	5.14	33.90	6.14	0.91	6.40	32.00	7.81	1.14
Pavia University	HSSF	9.67	28.42	9.31	1.48	10.91	27.38	10.21	1.66	12.70	26.05	12.01	1.92
	GTNN	12.70	26.05	12.22	1.88	14.09	25.15	13.29	2.08	16.23	23.92	14.86	2.37
	NSSR-AL	5.40	33.48	5.36	0.83	6.48	31.90	6.33	0.98	7.47	30.66	7.18	1.12
	AL-NSSR	4.96	34.23	5.23	0.78	5.95	32.63	6.08	0.93	8.41	29.64	8.07	1.32
	DDL	4.84	34.43	5.01	0.76	5.37	33.52	5.48	0.86	6.75	31.53	6.63	1.08
Cuprite Mine	HSSF	8.69	29.34	8.24	10.58	9.14	28.91	8.19	7.79	10.37	27.81	8.03	8.07
	GTNN	9.91	28.20	8.36	9.13	12.06	26.50	10.01	10.58	13.98	25.22	11.56	11.41
	NSSR-AL	4.68	34.72	4.26	2.24	5.23	33.76	4.85	5.07	6.46	31.93	5.95	6.27
	AL-NSSR	5.36	33.54	4.94	3.20	5.88	32.73	5.44	3.94	6.06	32.48	5.71	4.95
	DDL	4.58	34.90	4.22	2.28	5.07	34.02	4.68	2.43	5.09	33.99	4.82	2.85

Tab. 2 Comparison of experimental results of different spatio-spectral fusion algorithms with magnification factor of 16

图像	算法	$σ = 0.1$ 0				$σ = 0.12$				$σ = 0.15$
图像	算法	RMSE	PSNR/dB	SAM/（°）	ERGAS	RMSE	PSNR/dB	SAM/（°）	ERGAS	RMSE	PSNR/dB	SAM/（°）	ERGAS
Pavia Center	HSSF	10.09	28.05	11.22	1.69	10.60	27.62	12.01	1.80	11.49	26.92	12.83	1.90
	GTNN	10.24	27.92	12.19	1.62	11.61	26.84	13.51	1.83	14.06	25.17	15.66	2.21
	NSSR-AL	5.58	33.18	6.32	0.92	6.40	32.01	7.23	1.06	6.96	31.27	7.85	1.13
	AL-NSSR	5.53	33.28	6.73	0.98	8.02	30.05	9.15	1.43	9.09	28.96	10.61	1.62
	DDL	5.12	33.94	6.16	0.92	5.14	33.90	6.14	0.91	6.40	32.00	7.81	1.14
Pavia University	HSSF	9.67	28.42	9.31	1.48	10.91	27.38	10.21	1.66	12.70	26.05	12.01	1.92
	GTNN	12.70	26.05	12.22	1.88	14.09	25.15	13.29	2.08	16.23	23.92	14.86	2.37
	NSSR-AL	5.40	33.48	5.36	0.83	6.48	31.90	6.33	0.98	7.47	30.66	7.18	1.12
	AL-NSSR	4.96	34.23	5.23	0.78	5.95	32.63	6.08	0.93	8.41	29.64	8.07	1.32
	DDL	4.84	34.43	5.01	0.76	5.37	33.52	5.48	0.86	6.75	31.53	6.63	1.08
Cuprite Mine	HSSF	8.69	29.34	8.24	10.58	9.14	28.91	8.19	7.79	10.37	27.81	8.03	8.07
	GTNN	9.91	28.20	8.36	9.13	12.06	26.50	10.01	10.58	13.98	25.22	11.56	11.41
	NSSR-AL	4.68	34.72	4.26	2.24	5.23	33.76	4.85	5.07	6.46	31.93	5.95	6.27
	AL-NSSR	5.36	33.54	4.94	3.20	5.88	32.73	5.44	3.94	6.06	32.48	5.71	4.95
	DDL	4.58	34.90	4.22	2.28	5.07	34.02	4.68	2.43	5.09	33.99	4.82	2.85

Fig. 3 Box-plots of band-wise PSNR of Pavia Center image

Fig. 4 Spectral SAM error curves of Pavia Center image

Fig. 5 Fusion result and error images of different algorithms with σ=0.15

Fig. 6 Experimental result of real noisy band of Cuprite Mine image

References 27

[1]	GUERRI M F， DISTANTE C， SPAGNOLO P， et al. Deep learning techniques for hyperspectral image analysis in agriculture： a review［J］. ISPRS Open Journal of Photogrammetry and Remote Sensing， 2024， 12： No.100062.
[2]	GU Y， LIU T， GAO G， et al. Multimodal hyperspectral remote sensing： an overview and perspective ［J］. SCIENCE CHINA Information Sciences， 2021， 64（2）： No.121301.
[3]	WANG M， XU Y， WANG Z， et al. Deep margin cosine autoencoder-based medical hyperspectral image classification for tumor diagnosis ［J］. IEEE Transactions on Instrumentation and Measurement， 2023， 72： No.2520512.
[4]	赖星锦，郑致远，杜晓颜，等. 基于超像素锚图二重降维的高光谱聚类算法［J］. 计算机应用， 2022， 42（7）： 2088-2093.
	LAI X J， ZHENG Z Y， DU X Y， XU S， et al. Hyperspectral clustering algorithm by double dimension-reduction based on super-pixel and anchor graph ［J］. Journal of Computer Applications， 2022， 42（7）： 2088-2093.
[5]	聂江涛，张磊，魏巍，等. 高光谱图像超分辨率重建技术研究进展［J］. 中国图象图形学报， 2023， 28（6）： 1685-1697.
	NIE J T， ZHANG L， WEI W， et al. A survey of hyperspectral image super-resolution method ［J］. Journal of Image and Graphics， 2023， 28（6）： 1685-1697.
[6]	LI Q， WANG Q， LI X. Mixed 2D/3D convolutional network for hyperspectral image super-resolution ［J］. Remote Sensing， 2020， 12（10）： No.1660.
[7]	XU Y， HOU J， ZHU X， et al. Hyperspectral image super-resolution with ConvLSTM skip-connections ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2024， 62： No.5519016.
[8]	DONG W， FU F， SHI G， et al. Hyperspectral image super-resolution via non-negative structured sparse representation ［J］. IEEE Transactions on Image Processing， 2016， 25（5）： 2337-2352.
[9]	DIAN R， LI S. Hyperspectral image super-resolution via subspace-based low tensor multi-rank regularization ［J］. IEEE Transactions on Image Processing， 2019， 28（10）： 5135-5146.
[10]	YANG J， WU C， YOU T， et al. Hierarchical spatio-spectral fusion for hyperspectral image super resolution via sparse representation and pre-trained deep model ［J］. Knowledge-Based Systems， 2023， 260： No.110170.
[11]	FU X， LIANG H， JIA S. Mixed noise-oriented hyperspectral and multispectral image fusion ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2023， 61： No.5526916.
[12]	KESHAVA N， MUSTARD J F. Spectral unmixing ［J］. IEEE Signal Processing Magazine， 2002， 19（1）： 44-57.
[13]	YOKOYA N， YAIRI T， IWASAKI A. Coupled nonnegative matrix factorization unmixing for hyperspectral and multispectral data fusion ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2012， 50（2）： 528-537.
[14]	WU X， XIAO S， DONG W， et al. Coupled matrix factorization constrained deep hyperspectral and multispectral image fusion ［J］. IEEE Sensors Journal， 2024， 24（5）： 6392-6404.
[15]	HUANG B， SONG H， CUI H， et al. Spatial and spectral image fusion using sparse matrix factorization ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2014， 52（3）： 1693-1704.
[16]	DIAN R， LI S， FANG L. Learning a low tensor-train rank representation for hyperspectral image super-resolution ［J］. IEEE Transactions on Neural Networks and Learning Systems， 2019， 30（9）： 2672-2683.
[17]	PENG Y， LI W， LUO X， et al. Hyperspectral image super-resolution via sparsity regularization based spatial-spectral tensor subspace representation ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2024， 17： 11707-11722.
[18]	DIAN R， LIU Y， LI S. Hyperspectral image fusion via a novel generalized tensor nuclear norm regularization ［J］. IEEE Transactions on Neural Networks and Learning Systems， 2025， 36（4）： 7437-7448.
[19]	LI Q， YUAN Y， WANG Q. Multiscale factor joint learning for hyperspectral image super-resolution ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2023， 61： No.5523110.
[20]	LI J， ZHENG K， GAO L， et al. Enhanced deep image prior for unsupervised hyperspectral image super-resolution ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2025， 63： No.5504218.
[21]	YANG Y， WANG Y， WANG H， et al. Spectral enhanced sparse transformer network for hyperspectral super-resolution reconstruction ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2024， 17： 17278-17291.
[22]	LI J， ZHENG K， GAO L， et al. Model-informed multistage unsupervised network for hyperspectral image super-resolution ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2024， 62： No.5516117.
[23]	XU S， CAO X， PENG J， et al. Hyperspectral image denoising by asymmetric noise modeling ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022， 60： No.5545214.
[24]	MAIRAL J， BACH F， PONCE J， et al. Online dictionary learning for sparse coding ［C］// Proceedings of the 26th Annual International Conference on Machine Learning. New York： ACM， 2009： 689-696.
[25]	Grupo de Inteligencia Computacional. Hyperspectral remote sensing scenes ［EB/OL］. ［2025-06-04］. .
[26]	YUHAS R H， GOETZ A F H， BOARDMAN J W. Discrimination among semi-arid landscape endmembers using the spectral angle mapper （SAM） algorithm ［EB/OL］. ［2025-05-11］. .
[27]	WALD L. Quality of high resolution synthesised images： is there a simple criterion？［C］// Proceedings of the 3rd Conference “Fusion of Earth Data： Merging Point Measurements， Raster Maps and Remotely Sensed Images”. ［S.l.］： SEE/URISCA， 2000： 99-103.

Dynamic dictionary learning based spatio-spectral fusion for noisy hyper-spectral images

基于动态字典学习的含噪高光谱图像空谱融合

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 27

Related Articles 15

Recommended Articles

Metrics

[1]	Qiaoling QI, Xiaoxiao WANG, Qianqian ZHANG, Peng WANG, Yongfeng DONG. Label noise adaptive learning algorithm based on meta-learning [J]. Journal of Computer Applications, 2025, 45(7): 2113-2122.
[2]	Dawei YANG, Xihai XU, Wei SONG. Relation extraction method combining semantic enhancement and perception attention [J]. Journal of Computer Applications, 2025, 45(6): 1801-1808.
[3]	Shuang LIU, Daqing LIU, Jiana MENG, Di ZHAO. Hyper-relational knowledge graph completion method fusing noise filtering [J]. Journal of Computer Applications, 2025, 45(6): 1817-1826.
[4]	Chao XU, Shufen ZHANG, Haitian CHEN, Lulu PENG, Shuaihua ZHANG. Federated learning method based on adaptive differential privacy and client selection optimization [J]. Journal of Computer Applications, 2025, 45(2): 482-489.
[5]	Qianting ZHANG, Liying HU, Lifei CHEN. Robust shapelet representation method for time series [J]. Journal of Computer Applications, 2025, 45(2): 436-443.
[6]	Jinfu WU, Yi LIU. Fast adversarial training method based on random noise and adaptive step size [J]. Journal of Computer Applications, 2024, 44(6): 1807-1815.
[7]	Yifei SONG, Yi LIU. Fast adversarial training method based on data augmentation and label noise [J]. Journal of Computer Applications, 2024, 44(12): 3798-3807.
[8]	Yan SHI, Yue WU, Dongqing ZHAO. Hybrid intelligent reflecting surface and relay assisted secure transmission scheme based on cooperative interference [J]. Journal of Computer Applications, 2024, 44(12): 3893-3898.
[9]	Pengbo WANG, Wuyang SHAN, Jun LI, Mao TIAN, Deng ZOU, Zhanfeng FAN. Robust splicing forensic algorithm against high-intensity salt-and-pepper noise [J]. Journal of Computer Applications, 2024, 44(10): 3177-3184.
[10]	Yumin SONG, Hao SUN, Zhan LI, Chang’an LI, Xiaoshu QIAO. Hatch recognition algorithm of bulk cargo ship based on incomplete point cloud normal filtering and compensation [J]. Journal of Computer Applications, 2024, 44(1): 324-330.
[11]	Guolong YUAN, Yujin ZHANG, Yang LIU. Image tampering forensics network based on residual feedback and self-attention [J]. Journal of Computer Applications, 2023, 43(9): 2925-2931.
[12]	Feiqiao SHAN, Zhaowei WANG, Yue SHEN. Time synchronization method based on precision time protocol in industrial wireless sensor networks [J]. Journal of Computer Applications, 2023, 43(7): 2255-2260.
[13]	Mengyi LI, Xia FANG, Hongbo ZHENG, Xujia QIN. Oriented line integral convolution algorithm for flow field based on information entropy [J]. Journal of Computer Applications, 2023, 43(4): 1233-1239.
[14]	Boyi FU, Yuncong PENG, Xin LAN, Xiaolin QIN. Survey of label noise learning algorithms based on deep learning [J]. Journal of Computer Applications, 2023, 43(3): 674-684.
[15]	Peng WANG, Dawei ZHANG, Zhengjun LU, Linhao LI. Moving object detection based on reliability low-rank factorization and generalized diversity difference [J]. Journal of Computer Applications, 2023, 43(2): 514-520.