《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (8): 2571-2577.DOI: 10.11772/j.issn.1001-9081.2021061126
• 多媒体计算与计算机仿真 • 上一篇
收稿日期:
2021-07-02
修回日期:
2021-09-05
接受日期:
2021-09-14
发布日期:
2021-12-27
出版日期:
2022-08-10
通讯作者:
叶志伟
作者简介:
靳华中(1973—),男,湖北洪湖人,副教授,博士,CCF会员,主要研究方向:计算机视觉、智能系统;Huazhong JIN, Xiuyang ZHANG, Zhiwei YE(), Wenqi ZHANG, Xiaoyu XIA
Received:
2021-07-02
Revised:
2021-09-05
Accepted:
2021-09-14
Online:
2021-12-27
Published:
2022-08-10
Contact:
Zhiwei YE
About author:
JIN Huazhong, born in 1973, Ph. D., associate professor. His research interests include computer vision, smart system.Supported by:
摘要:
针对图像去噪中的去噪效果差、训练周期长的问题,提出一种基于近似U型网络结构的图像去噪模型。首先,使用不同步长的卷积层将原有的线性网络结构修改为近似U型的网络结构;然后,将不同感受野的图像信息叠加以尽可能地保留图像的原有信息;最后,引入反卷积网络层进行图像恢复和噪声的进一步去除。在Set12与BSD68测试集上与去噪卷积神经网络(DnCNN)模型相比,所提模型的峰值信噪比(PSNR)平均提升了0.04~0.14 dB,训练时长平均缩短了41%。实验结果表明,所提模型具有更好地去噪效果和更短的训练时长。
中图分类号:
靳华中, 张修洋, 叶志伟, 张闻其, 夏小鱼. 基于近似U型网络结构的图像去噪模型[J]. 计算机应用, 2022, 42(8): 2571-2577.
Huazhong JIN, Xiuyang ZHANG, Zhiwei YE, Wenqi ZHANG, Xiaoyu XIA. Image denoising model based on approximate U-shaped network structure[J]. Journal of Computer Applications, 2022, 42(8): 2571-2577.
噪声σ | BM3D | WNNM | EPLL | MLP | CSF | TNRD | DnCNN-B | 本文模型 |
---|---|---|---|---|---|---|---|---|
15 | 31.07 | 31.37 | 31.21 | — | 31.24 | 31.42 | 31.61 | 31.72 |
25 | 28.57 | 28.83 | 28.68 | 28.96 | 28.74 | 28.92 | 29.16 | 29.23 |
50 | 25.62 | 25.87 | 25.67 | 26.03 | — | 25.97 | 26.23 | 26.27 |
表1 不同模型在BSD68数据集上的峰值信噪比对比 ( dB)
Tab. 1 PSNR comparison of different models on BSD68 dataset
噪声σ | BM3D | WNNM | EPLL | MLP | CSF | TNRD | DnCNN-B | 本文模型 |
---|---|---|---|---|---|---|---|---|
15 | 31.07 | 31.37 | 31.21 | — | 31.24 | 31.42 | 31.61 | 31.72 |
25 | 28.57 | 28.83 | 28.68 | 28.96 | 28.74 | 28.92 | 29.16 | 29.23 |
50 | 25.62 | 25.87 | 25.67 | 26.03 | — | 25.97 | 26.23 | 26.27 |
图片 | BM3D | WNNM | EPLL | CSF | TNRD | DnCNN-B | 本文模型 |
---|---|---|---|---|---|---|---|
平均 | 32.372 | 32.696 | 32.138 | 32.318 | 32.502 | 32.680 | 32.824 |
C.man | 31.91 | 32.17 | 31.85 | 31.95 | 32.19 | 32.10 | 32.50 |
House | 34.93 | 35.13 | 34.17 | 34.39 | 34.53 | 34.93 | 35.03 |
Peppers | 32.69 | 32.99 | 32.64 | 32.85 | 33.04 | 33.15 | 33.12 |
Starfish | 31.14 | 31.82 | 31.13 | 31.55 | 31.75 | 32.02 | 32.14 |
Monar | 31.85 | 32.71 | 32.10 | 32.33 | 32.56 | 32.94 | 33.25 |
Airpl | 31.07 | 31.39 | 31.19 | 31.33 | 31.46 | 31.56 | 31.65 |
Parrot | 31.37 | 31.62 | 31.42 | 31.37 | 31.63 | 31.63 | 31.85 |
Lena | 34.26 | 34.27 | 33.92 | 34.06 | 34.24 | 34.56 | 34.56 |
Barbara | 33.10 | 33.60 | 31.38 | 31.92 | 32.13 | 32.09 | 32.64 |
Boat | 32.13 | 32.27 | 31.93 | 32.01 | 32.14 | 32.35 | 32.32 |
Man | 31.92 | 32.11 | 32.00 | 32.08 | 32.23 | 32.41 | 32.40 |
Couple | 32.10 | 32.17 | 31.93 | 31.98 | 32.11 | 32.41 | 32.43 |
表2 Set12数据集中每幅图片的峰值信噪比对比(σ = 15) ( dB)
Tab. 2 PSNR comparison of each picture in Set12 dataset (σ = 15)
图片 | BM3D | WNNM | EPLL | CSF | TNRD | DnCNN-B | 本文模型 |
---|---|---|---|---|---|---|---|
平均 | 32.372 | 32.696 | 32.138 | 32.318 | 32.502 | 32.680 | 32.824 |
C.man | 31.91 | 32.17 | 31.85 | 31.95 | 32.19 | 32.10 | 32.50 |
House | 34.93 | 35.13 | 34.17 | 34.39 | 34.53 | 34.93 | 35.03 |
Peppers | 32.69 | 32.99 | 32.64 | 32.85 | 33.04 | 33.15 | 33.12 |
Starfish | 31.14 | 31.82 | 31.13 | 31.55 | 31.75 | 32.02 | 32.14 |
Monar | 31.85 | 32.71 | 32.10 | 32.33 | 32.56 | 32.94 | 33.25 |
Airpl | 31.07 | 31.39 | 31.19 | 31.33 | 31.46 | 31.56 | 31.65 |
Parrot | 31.37 | 31.62 | 31.42 | 31.37 | 31.63 | 31.63 | 31.85 |
Lena | 34.26 | 34.27 | 33.92 | 34.06 | 34.24 | 34.56 | 34.56 |
Barbara | 33.10 | 33.60 | 31.38 | 31.92 | 32.13 | 32.09 | 32.64 |
Boat | 32.13 | 32.27 | 31.93 | 32.01 | 32.14 | 32.35 | 32.32 |
Man | 31.92 | 32.11 | 32.00 | 32.08 | 32.23 | 32.41 | 32.40 |
Couple | 32.10 | 32.17 | 31.93 | 31.98 | 32.11 | 32.41 | 32.43 |
图片 | BM3D | WNNM | EPLL | MLP | CSF | TNRD | DnCNN-B | 本文模型 |
---|---|---|---|---|---|---|---|---|
平均 | 29.969 | 30.257 | 29.692 | 30.027 | 29.837 | 30.055 | 30.362 | 30.457 |
C.man | 29.45 | 29.64 | 29.26 | 29.61 | 29.48 | 29.72 | 29.94 | 30.12 |
House | 32.85 | 33.22 | 32.17 | 32.56 | 32.39 | 32.53 | 33.05 | 33.13 |
Peppers | 30.16 | 30.42 | 30.17 | 30.30 | 30.32 | 30.57 | 30.84 | 30.80 |
Starfish | 28.56 | 29.03 | 28.51 | 28.82 | 28.80 | 29.02 | 29.34 | 29.45 |
Monar | 29.25 | 29.84 | 29.39 | 29.61 | 29.62 | 29.85 | 30.25 | 30.43 |
Airpl | 28.42 | 28.69 | 28.61 | 28.82 | 28.72 | 28.88 | 29.09 | 29.14 |
Parrot | 28.93 | 29.15 | 28.95 | 29.25 | 28.90 | 29.18 | 29.35 | 29.51 |
Lena | 32.07 | 32.24 | 31.73 | 32.25 | 31.79 | 32.00 | 32.42 | 32.47 |
Barbara | 30.71 | 31.24 | 28.61 | 29.54 | 29.03 | 29.41 | 29.69 | 30.09 |
Boat | 29.90 | 30.03 | 29.74 | 29.97 | 29.76 | 29.91 | 30.20 | 30.18 |
Man | 29.61 | 29.76 | 29.66 | 29.88 | 29.71 | 29.87 | 30.09 | 30.04 |
Couple | 29.71 | 29.82 | 29.53 | 29.73 | 29.53 | 29.71 | 30.10 | 30.12 |
表3 Set12数据集中每幅图片的峰值信噪比对比(σ = 25) ( dB)
Tab. 3 PSNR comparison of each picture in Set12 dataset (σ = 25)
图片 | BM3D | WNNM | EPLL | MLP | CSF | TNRD | DnCNN-B | 本文模型 |
---|---|---|---|---|---|---|---|---|
平均 | 29.969 | 30.257 | 29.692 | 30.027 | 29.837 | 30.055 | 30.362 | 30.457 |
C.man | 29.45 | 29.64 | 29.26 | 29.61 | 29.48 | 29.72 | 29.94 | 30.12 |
House | 32.85 | 33.22 | 32.17 | 32.56 | 32.39 | 32.53 | 33.05 | 33.13 |
Peppers | 30.16 | 30.42 | 30.17 | 30.30 | 30.32 | 30.57 | 30.84 | 30.80 |
Starfish | 28.56 | 29.03 | 28.51 | 28.82 | 28.80 | 29.02 | 29.34 | 29.45 |
Monar | 29.25 | 29.84 | 29.39 | 29.61 | 29.62 | 29.85 | 30.25 | 30.43 |
Airpl | 28.42 | 28.69 | 28.61 | 28.82 | 28.72 | 28.88 | 29.09 | 29.14 |
Parrot | 28.93 | 29.15 | 28.95 | 29.25 | 28.90 | 29.18 | 29.35 | 29.51 |
Lena | 32.07 | 32.24 | 31.73 | 32.25 | 31.79 | 32.00 | 32.42 | 32.47 |
Barbara | 30.71 | 31.24 | 28.61 | 29.54 | 29.03 | 29.41 | 29.69 | 30.09 |
Boat | 29.90 | 30.03 | 29.74 | 29.97 | 29.76 | 29.91 | 30.20 | 30.18 |
Man | 29.61 | 29.76 | 29.66 | 29.88 | 29.71 | 29.87 | 30.09 | 30.04 |
Couple | 29.71 | 29.82 | 29.53 | 29.73 | 29.53 | 29.71 | 30.10 | 30.12 |
图片 | BM3D | WNNM | EPLL | MLP | TNRD | DnCNN-B | 本文模型 |
---|---|---|---|---|---|---|---|
平均 | 26.722 | 27.052 | 26.471 | 26.783 | 26.812 | 27.206 | 27.248 |
C.man | 26.13 | 26.45 | 26.10 | 26.37 | 26.62 | 27.03 | 27.20 |
House | 26.69 | 30.33 | 29.12 | 29.64 | 29.48 | 30.02 | 30.34 |
Peppers | 26.68 | 26.95 | 26.80 | 26.68 | 27.10 | 27.39 | 27.35 |
Starfish | 25.04 | 25.44 | 25.12 | 25.43 | 25.42 | 25.72 | 25.80 |
Monar | 25.82 | 26.32 | 25.94 | 26.26 | 26.31 | 26.83 | 26.79 |
Airpl | 25.10 | 25.42 | 25.31 | 25.56 | 25.59 | 25.89 | 25.86 |
Parrot | 25.90 | 26.14 | 25.95 | 26.12 | 26.16 | 26.48 | 26.46 |
Lena | 29.05 | 29.25 | 28.68 | 29.32 | 28.93 | 29.38 | 29.47 |
Barbara | 27.22 | 27.79 | 24.83 | 25.24 | 25.70 | 26.38 | 26.39 |
Boat | 26.78 | 26.97 | 26.74 | 27.03 | 26.94 | 27.23 | 27.15 |
Man | 26.81 | 26.94 | 26.79 | 27.06 | 26.98 | 27.23 | 27.19 |
Couple | 26.46 | 26.64 | 26.30 | 26.67 | 26.50 | 26.91 | 26.97 |
表4 Set12数据集中每幅图片的峰值信噪比对比(σ = 50) ( dB)
Tab. 4 PSNR comparison of each picture in Set12 dataset (σ = 50)
图片 | BM3D | WNNM | EPLL | MLP | TNRD | DnCNN-B | 本文模型 |
---|---|---|---|---|---|---|---|
平均 | 26.722 | 27.052 | 26.471 | 26.783 | 26.812 | 27.206 | 27.248 |
C.man | 26.13 | 26.45 | 26.10 | 26.37 | 26.62 | 27.03 | 27.20 |
House | 26.69 | 30.33 | 29.12 | 29.64 | 29.48 | 30.02 | 30.34 |
Peppers | 26.68 | 26.95 | 26.80 | 26.68 | 27.10 | 27.39 | 27.35 |
Starfish | 25.04 | 25.44 | 25.12 | 25.43 | 25.42 | 25.72 | 25.80 |
Monar | 25.82 | 26.32 | 25.94 | 26.26 | 26.31 | 26.83 | 26.79 |
Airpl | 25.10 | 25.42 | 25.31 | 25.56 | 25.59 | 25.89 | 25.86 |
Parrot | 25.90 | 26.14 | 25.95 | 26.12 | 26.16 | 26.48 | 26.46 |
Lena | 29.05 | 29.25 | 28.68 | 29.32 | 28.93 | 29.38 | 29.47 |
Barbara | 27.22 | 27.79 | 24.83 | 25.24 | 25.70 | 26.38 | 26.39 |
Boat | 26.78 | 26.97 | 26.74 | 27.03 | 26.94 | 27.23 | 27.15 |
Man | 26.81 | 26.94 | 26.79 | 27.06 | 26.98 | 27.23 | 27.19 |
Couple | 26.46 | 26.64 | 26.30 | 26.67 | 26.50 | 26.91 | 26.97 |
噪声σ | DnCNN-B | 本文模型 | 差值 |
---|---|---|---|
10 | 34.63 | 34.77 | +0.14 |
15 | 32.68 | 32.82 | +0.14 |
20 | 31.42 | 31.53 | +0.11 |
25 | 30.36 | 30.46 | +0.10 |
30 | 29.46 | 29.55 | +0.09 |
35 | 28.82 | 28.89 | +0.07 |
40 | 28.16 | 28.23 | +0.07 |
45 | 27.65 | 27.70 | +0.05 |
50 | 27.21 | 27.25 | +0.04 |
表5 Set12数据集上不同噪声强度下本文模型与DnCNN模型对比
Tab. 5 Comparison of the proposed model and DnCNN model under different noise intensities on Set12 dataset
噪声σ | DnCNN-B | 本文模型 | 差值 |
---|---|---|---|
10 | 34.63 | 34.77 | +0.14 |
15 | 32.68 | 32.82 | +0.14 |
20 | 31.42 | 31.53 | +0.11 |
25 | 30.36 | 30.46 | +0.10 |
30 | 29.46 | 29.55 | +0.09 |
35 | 28.82 | 28.89 | +0.07 |
40 | 28.16 | 28.23 | +0.07 |
45 | 27.65 | 27.70 | +0.05 |
50 | 27.21 | 27.25 | +0.04 |
噪声σ | 采用步长 | 峰值信噪比/dB | 训练时长/s |
---|---|---|---|
15 | 1 | 32.80 | 7 543 |
2 | 32.82 | 4 752 | |
25 | 1 | 30.30 | 7 543 |
2 | 30.46 | 4 752 | |
50 | 1 | 27.16 | 7 543 |
2 | 27.25 | 4 752 |
表6 Set12数据集上不同步长网络峰值信噪比与训练时长对比
Tab. 6 Comparison of PSNR and training time for networks with different strides on Set12 dataset
噪声σ | 采用步长 | 峰值信噪比/dB | 训练时长/s |
---|---|---|---|
15 | 1 | 32.80 | 7 543 |
2 | 32.82 | 4 752 | |
25 | 1 | 30.30 | 7 543 |
2 | 30.46 | 4 752 | |
50 | 1 | 27.16 | 7 543 |
2 | 27.25 | 4 752 |
模型 | 耗时/s |
---|---|
WNNM | 240.56 |
EPLL | 53.53 |
DnCNN-B | 0.02 |
本文模型 | 0.01 |
表7 各模型执行时间对比 (s)
Tab. 7 Comparison of execution time of each model
模型 | 耗时/s |
---|---|
WNNM | 240.56 |
EPLL | 53.53 |
DnCNN-B | 0.02 |
本文模型 | 0.01 |
1 | 刘利平,乔乐乐,蒋柳成.图像去噪方法概述[J].计算机科学与探索, 2021, 15(8): 1418-1431. 10.3778/j.issn.1673-9418.2101035 |
LIU L P, QIAO L L, JIANG L C. Overview of image denoising methods[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(8): 1418-1431. 10.3778/j.issn.1673-9418.2101035 | |
2 | 方莉,张萍.经典图像去噪算法研究综述[J].工业控制计算机, 2010, 23(11): 73-74. 10.3969/j.issn.1001-182X.2010.11.034 |
FANG L, ZHANG P. Overview on some arithmetics for image denoising[J]. Industrial Control Computer, 2010, 23(11): 73-74. 10.3969/j.issn.1001-182X.2010.11.034 | |
3 | DABOV K, FOI A, KATKOVNIK V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Transactions on Image Processing, 2007, 16(8): 2080-2095. 10.1109/tip.2007.901238 |
4 | MAIRAL J, BACH F, PONCE J, et al. Non-local sparse models for image restoration [C]// Proceedings of the IEEE 12th International Conference on Computer Vision. Piscataway: IEEE, 2010: 2272-2279. |
5 | DONG W S, ZHANG L, SHI G M, et al. Nonlocally centralized sparse representation for image restoration[J]. IEEE Transactions on Image Processing, 2013, 22(4): 1620-1630. 10.1109/tip.2012.2235847 |
6 | GU S H, ZHANG L, ZUO W M, et al. Weighted nuclear norm minimization with application to image denoising [C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 2862-2869. 10.1109/cvpr.2014.366 |
7 | SCHMIDT U, ROTH S. Shrinkage fields for effective image restoration [C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 2774-2781. 10.1109/cvpr.2014.349 |
8 | CHEN Y J, YU W, POCK T. On learning optimized reaction diffusion processes for effective image restoration [C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 5261-5269. 10.1109/cvpr.2015.7299163 |
9 | ZHANG K, ZUO W M, CHEN Y J, et al. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2016, 26(7): 3142-3155. 10.1109/tip.2017.2662206 |
10 | KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [C]// Proceedings of the 25th International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2012: 1097-1105. |
11 | IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift [C]// Proceedings of the 32nd International Conference on Machine Learning. New York: JMLR.org, 2015: 448-456. |
12 | HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. 10.1109/cvpr.2016.90 |
13 | 靳华中,刘阳,叶志伟.一种改进的深度网络残差学习的图像降噪方法[J].华中师范大学学报(自然科学版), 2020, 54(6): 949-955, 968. 10.19603/j.cnki.1000-1190.2020.06.006 |
JIN H Z, LIU Y, YE Z W. An improved image denoising method of depth network residual learning[J]. Journal of Central China Normal University (Natural Sciences), 2020, 54(6): 949-955, 968. 10.19603/j.cnki.1000-1190.2020.06.006 | |
14 | ZEILER M D, TAYLOR G W, FERGUS R. Adaptive deconvolutional networks for mid and high level feature learning [C]// Proceedings of the 2011 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2011: 2018-2025. 10.1109/iccv.2011.6126474 |
15 | RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation [C]// Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham: Springer, 2015: 234-241. |
16 | SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions [C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 1-9. 10.1109/cvpr.2015.7298594 |
17 | SCHMIDT U, JANCSARY J, NOWOZIN S, et al. Cascades of regression tree fields for image restoration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(4): 677-689. 10.1109/tpami.2015.2441053 |
18 | ROTH S, BLACK M J. Fields of experts[J]. International Journal of Computer Vision, 2009, 82(2): 205-229. 10.1007/s11263-008-0197-6 |
19 | GU S H, XIE Q, MENG D Y, et al. Weighted nuclear norm minimization and its applications to low level vision[J]. International Journal of Computer Vision, 2017, 121(2): 183-208. 10.1007/s11263-016-0930-5 |
20 | SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. (2015-04-10) [2021-03-23]. . |
21 | CHEN Y J, POCK T. Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1256-1272. 10.1109/tpami.2016.2596743 |
[1] | 余晓鹏, 何儒汉, 黄晋, 张俊杰, 胡新荣. 基于改进Inception结构的知识图谱嵌入模型[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1065-1071. |
[2] | 曹一珉, 蔡磊, 高敬阳. 基于生成对抗网络的基因数据生成方法[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 783-790. |
[3] | 徐光柱, 林文杰, 陈莎, 匡婉, 雷帮军, 周军. U-Net与自适应阈值脉冲耦合神经网络相结合的眼底血管分割方法[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 825-832. |
[4] | 李恒鑫, 常侃, 谭宇飞, 凌铭阳, 覃团发. 应用通道间相关性及增强信息蒸馏的彩色图像去马赛克网络[J]. 《计算机应用》唯一官方网站, 2022, 42(1): 245-251. |
[5] | 卞凌志, 王直杰. 基于增强多维多粒度级联森林的信用评分模型[J]. 计算机应用, 2021, 41(9): 2539-2544. |
[6] | 黄梨, 卢龙. 基于长距离依赖编码与深度残差U-Net的缺血性卒中病灶分割[J]. 计算机应用, 2021, 41(6): 1820-1827. |
[7] | 牛康力, 谌雨章, 沈君凤, 曾张帆, 潘永才, 王绎冲. 基于深度学习的双通道夜视图像复原方法[J]. 计算机应用, 2021, 41(6): 1775-1784. |
[8] | 梁敏, 王昊榕, 张瑶, 李杰. 基于加速残差网络的图像超分辨率重建方法[J]. 计算机应用, 2021, 41(5): 1438-1444. |
[9] | 高海军, 曾祥银, 潘大志, 郑伯川. 基于U-Net改进模型的直肠肿瘤分割方法[J]. 计算机应用, 2020, 40(8): 2392-2397. |
[10] | 石陆魁, 马红祺, 张朝宗, 樊世燕. 基于改进残差结构的肺结节检测方法[J]. 计算机应用, 2020, 40(7): 2110-2116. |
[11] | 马金林, 魏萌, 马自萍. 基于深度迁移学习的肺结节分割方法[J]. 计算机应用, 2020, 40(7): 2117-2125. |
[12] | 胡雪影, 郭海儒, 朱蓉. 基于混合深度卷积网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(7): 2069-2076. |
[13] | 陈赛健, 朱远平. 基于生成对抗网络的文本图像联合超分辨率与去模糊方法[J]. 计算机应用, 2020, 40(3): 859-864. |
[14] | 魏小娜, 邢嘉祺, 王振宇, 王颖珊, 石洁, 赵地, 汪红志. 基于改进U-Net的关节滑膜磁共振图像的分割[J]. 计算机应用, 2020, 40(11): 3340-3345. |
[15] | 张强, 杨剑, 富丽贞. 双输入流深度反卷积的插值神经网络[J]. 计算机应用, 2019, 39(8): 2271-2275. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||