×
模态框(Modal)标题
在这里添加一些文本
Close
Close
Submit
Cancel
Confirm
×
模态框(Modal)标题
×
Toggle navigation
Home
About Journal
Download
Archive
Contact Us
Figure/Table detail
Image super⁃resolution algorithm joint deep belief network and neighborhood regression
Weiqin Huang, Fengqiang Gao, Junren Chen, Chan Li
Journal of Nanjing University(Natural Sciences)
, 2019, 55(
4
): 581-591. DOI:
10.13232/j.cnki.jnju.2019.04.008
无参考指标
平均梯度
信息熵
Brenner函数
能量函数
原始图
2.9443
6.6701
4261738
3379712
DBNNR
3.6527
6.7088
6087568
5284806
Table 3
The average of no reference indices between original medical images and reconstructed images
Other figure/table from this article
Fig.1
The model of RBM
Fig.2
The model of DBN with three RBM layers
Fig.3
The relationship between dictionary learning and neural network representation
Fig.4
Processing of sample feature images
Fig.5
The dictionary learning model based on DBN
Fig.6
The flow chart of algorithm
Fig.7
The relationship between the neighborhood size and reconstruction quality
Table 1
PSNR
and
SSIM
values corresponding to reconstructed images of different SR algorithms
Fig.8
Test images for subjective evaluation
Fig.9
Comparison of the reconstructed image detail with difference SR algorithm for Head
Table 2
Average reconstruction time(unit:s) of Set5 and Set14 for different SR algorithms
Fig.10
Comparison of the reconstructed image detail with difference SR algorithm for Zebra
Fig.11
Sample images for dictionary learning
Fig.12
Comparison of the original image and
Fig.13
Comparison of the original image and