Journals
Advanced Photonics
Photonics Insights
Advanced Photonics Nexus
Photonics Research
Advanced Imaging
View All Journals
Chinese Optics Letters
High Power Laser Science and Engineering
Articles
Optics
Physics
Geography
View All Subjects
Conferences
CIOP
HPLSE
AP
View All Events
News
About CLP
Search by keywords or author
Login
Registration
Login in
Registration
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
metasurface
laser
polarization
nir
lithium niobate
optical coherence tomography
Journals >
Laser & Optoelectronics Progress >
Volume 58 >
Issue 4 >
Page 0410012 > Article
Laser & Optoelectronics Progress
Vol. 58, Issue 4, 0410012 (2021)
Text Image Generation Method with Scene Description
Youwen Huang, Bin Zhou
*
, and Xin Tang
Author Affiliations
School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China
show less
DOI:
10.3788/LOP202158.0410012
Cite this Article
Set citation alerts
Youwen Huang, Bin Zhou, Xin Tang. Text Image Generation Method with Scene Description[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0410012
Copy Citation Text
EndNote(RIS)
BibTex
Plain Text
show less
Fig. 1.
Generation network model
Download full size
Fig. 2.
Mask generation network
Download full size
Fig. 3.
Discrimination network model
Download full size
Fig. 4.
Layout discriminator
Download full size
Fig. 5.
Comparison results of same description
Download full size
Fig. 6.
Comparison results after adding objects
Download full size
Fig. 7.
Comparison results of predicted mask
Download full size
t
0.3
0.4
0.5
0.6
0.7
Number of objects
156
151
146
127
103
Number of relationship types
38
38
37
30
24
Table 1.
Preprocessing results under different threshold values
Model
IS
FID
Real image(64×64)
13.90±0.50
0
Proposed model(no
D
layout
)
6.72±0.24
57.48
Proposed model(no
G
mask
)
6.69±0.14
61.34
Proposed model(full model)
7.11±0.14
42.20
Sg2im
[
11
]
6.30±0.20
73.39
StackGAN
[
8
]
6.35±0.16
108.68
AttnGAN
[
10
]
6.38±0.22
96.40
Table 2.
Comparison results of IS and FID values
Model
Proposed model(full model)
Sg2im
[
11
]
StackGAN
[
8
]
AttnGAN
[
10
]
Time/s
0.0278
0.0216
0.0634
0. 0302
Table 3.
Comparison results of image generation time
Abstract
Get PDF(in Chinese)
Figures&Tables (10)
Equations (0)
References (20)
Get Citation
Copy Citation Text
Youwen Huang, Bin Zhou, Xin Tang. Text Image Generation Method with Scene Description[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0410012
Download Citation
EndNote(RIS)
BibTex
Plain Text
Set citation alerts for the article
Tools
Share
Set citation alerts for the article
Save the article for my favorites
Paper Information
Category: Image Processing
Received: Jun. 30, 2020
Accepted: Aug. 7, 2020
Published Online: Feb. 23, 2021
The Author Email: Zhou Bin (zhoubin_master@163.com)
DOI:
10.3788/LOP202158.0410012
Recommended Topics
laser devices and laser physics
Lasers and Laser Optics
Laser physics
laser manufacturing
Instrumentation, Measurement and Metrology
Set citation alerts for the article
Please enter your email address
Cancel
Confirm