功能型复合深度网络的图像超分辨率重建
Image Super-resolution Reconstruction of Functional Composite Deep Network
查看参考文献40篇
文摘
|
针对现有单图像超分辨率重建时主要采用的简单链式堆叠的单一网络存在层间联系弱、网络关注点单一以及分层特征不能充分利用等问题,提出了一种复合的深度神经网络用于提升图像超分辨重建性能。该方法首先使用特征提取层提取低分辨率图像的初始特征;再将初始特征分别送入两个子网络,一个子网络负责图像细节的提取与运算,另一子网络负责图像噪声降解与消除;然后将两个子网络输出的深层次抽象特征与初始特征相结合,最后通过重建层获得超分辨率图像。以峰值信噪比(PSNR)与结构相似性(SSIM)为评价指标,在Set14测试集上使用放大因子3进行实验,将复合网络与算法Bicubic、SelfEx、SRCNN、VDSR和RED等进行对比,实验结果发现,PSNR分别提高了2.27 dB、0.66 dB、0.54 dB、0.05 dB、0.21 dB,而SSIM则分别提高了6.08、1.54、1.41、0.36、0.09个百分点。 |
其他语种文摘
|
Aiming at the problems of weak inter-layer connections, single network concerns and insufficient utilization of layered features in the existing single- image super- resolution reconstruction using simple chain- stacked single network, a composite depth neural network is proposed to improve the performance of image super- resolution reconstruction.Firstly, feature extraction layer is used to extract the initial features of low-resolution images.Then, the initial features are fed into two sub-networks, one is responsible for image detail extraction and calculation, the other is responsible for image noise degradation and elimination.Then the deep abstract features output by the two sub-networks are combined with the initial features, and finally the super- resolution image is obtained through the reconstruction layer.Taking peak signal-to-noise ratio(PSNR)and structural similarity(SSIM)as evaluation indices, the experiment is carried out by using amplification factor 3 in Set14 test set.The experimental results show that PSNR is increased by 2.27 dB, 0.66 dB, 0.54 dB, 0.05 dB and 0.21 dB respectively, while SSIM is improved by 6.08, 1.54, 1.41, 0.36,0.09 percentage points by comparing the combined network with algorithms Bicubic, SelfEx, SRCNN, VDSR and RED. |
来源
|
计算机科学与探索
,2020,14(8):1368-1379 【核心库】
|
DOI
|
10.3778/j.issn.1673-9418.1909006
|
关键词
|
单图像超分辨率重建
;
卷积神经网络(CNN)
;
复合网络
;
子网络
;
特征结合
|
地址
|
1.
昆明理工大学信息工程与自动化学院, 昆明, 650000
2.
中国科学院云南天文台, 昆明, 650000
3.
河南理工大学计算机学院, 河南, 焦作, 454150
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1673-9418 |
学科
|
自动化技术、计算机技术 |
基金
|
国家自然科学基金
|
文献收藏号
|
CSCD:6781217
|
参考文献 共
40
共2页
|
1.
苏衡. 超分辨率图像重建方法综述.
自动化学报,2013,39(8):1202-1213
|
CSCD被引
99
次
|
|
|
|
2.
Glasner D. Super-resolution from a single image.
Proceedings of the 12th IEEE International Conference on Computer Vision, Kyoto, Sep 27-Oct 4, 2009,2009:349-356
|
CSCD被引
1
次
|
|
|
|
3.
Park S C. Super-resolution image reconstruction: a technical overview.
IEEE Signal Processing Magazine,2003,20(3):21-36
|
CSCD被引
240
次
|
|
|
|
4.
王会鹏. 一种基于区域的双三次图像插值算法.
计算机工程,2010,36(19):216-218
|
CSCD被引
20
次
|
|
|
|
5.
Yang J C. Image super-resolution via sparse representation.
IEEE Transactions on Image Processing,2010,19(11):2861-2873
|
CSCD被引
189
次
|
|
|
|
6.
Timofte R. A+: adjusted anchored neighborhood regression for fast super-resolution.
LNCS 9006: Proceedings of the 12th Asian Conference on Computer Vision, Singapore, Nov 1-5, 2014,2015:111-126
|
CSCD被引
8
次
|
|
|
|
7.
Huang J B. Single image super-resolution from transformed self-exemplars.
Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, Jun 7-12, 2015,2015:5197-5206
|
CSCD被引
3
次
|
|
|
|
8.
Hayat K. Multimedia super-resolution via deep learning: a survey.
Digital Signal Processing,2018,81(10):198-217
|
CSCD被引
4
次
|
|
|
|
9.
谭政. 一种基于频域的序列图像超分辨率增强方法.
光学学报,2017,37(7):83-88
|
CSCD被引
1
次
|
|
|
|
10.
朱福珍. 改进的稀疏表示遥感图像超分辨重建.
光学精密工程,2019,27(3):718-725
|
CSCD被引
21
次
|
|
|
|
11.
Zeiler M D. Visualizing and understanding convolutional networks.
LNCS 8689: Proceedings of the 13th European Conference on Computer Visio, Zurich, Sep 6-12, 2014,2014:818-833
|
CSCD被引
56
次
|
|
|
|
12.
Deng J. ImageNet: a large-scale hierarchical image database.
Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami, Jun 20-25, 2009,2009:248-255
|
CSCD被引
2
次
|
|
|
|
13.
Dong C. Image super-resolution using deep convolutional networks.
IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,38(2):295-307
|
CSCD被引
22
次
|
|
|
|
14.
Graves A. Speech recognition with deep recurrent neural networks.
Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, May 26-31, 2013,2013:6645-6649
|
CSCD被引
1
次
|
|
|
|
15.
He K M. Deep residual learning for image recognition.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016,2016:770-778
|
CSCD被引
34
次
|
|
|
|
16.
Kim J. Deeply-recursive convolutional network for image super-resolution.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30,2016,2016:1637-1645
|
CSCD被引
3
次
|
|
|
|
17.
Kim J. Accurate image super-resolution using very deep convolutional networks.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30,2016,2016:1646-1654
|
CSCD被引
2
次
|
|
|
|
18.
Mao X J. Image restoration using convolutional auto-encoders with symmetric skip connections.
arXiv:1606.08921,2016
|
CSCD被引
8
次
|
|
|
|
19.
Radford A. Unsupervised representation learning with deep convolutional generative adversarial networks.
arXiv:1511.06434,2015
|
CSCD被引
127
次
|
|
|
|
20.
Ledig C. Photo-realistic single image super-resolution using a generative adversarial network.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017,2017:105-114
|
CSCD被引
10
次
|
|
|
|
|