Uneingeschränkter Zugang

Super-resolution Image Reconstruction Based on Double Regression Network Model

Jieyi Lv

Jieyi Lv

School of Computer Science and Engineering, Xi’an Technological UniversityXi’an, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Lv, Jieyi
 und 
Zhongsheng Wang

Zhongsheng Wang

School of Computer Science and Engineering, Xi’an Technological UniversityXi’an, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Wang, Zhongsheng
  
26. Mai 2023
Super-resolution Image Reconstruction Based on Double Regression Network Model's Cover Image
Über diesen Artikel
Vorheriger Artikel
Nächster Artikel
Zitieren
COVER HERUNTERLADEN
Online veröffentlicht: 26. Mai 2023
Seitenbereich: 82 - 88
DOI: https://doi.org/10.2478/ijanmc-2022-0039
Schlüsselwörter
© 2022 Jieyi Lv et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Composition of double regression model
Composition of double regression model

Figure 2.

Super resolution reconstruction process
Super resolution reconstruction process

Figure 3.

Recursive learning
Recursive learning

Figure 4.

Double magnification reconstruction comparison of each algorithm
Double magnification reconstruction comparison of each algorithm

Figure 5.

Comparison of four times magnification reconstruction of each algorithm
Comparison of four times magnification reconstruction of each algorithm

Comparison of the results of PSNR reconstruction by two times of each algorithm

Datasets FSRCNN SRGAN ESRGAN Ours
Set5 32.40 33.19 33.46 34.68
Set14 29.52 29.56 29.47 30.56
Bsd100 26.74 29.47 29.78 29.78

Comparison of SSIM results of four times reconstruction of each algorithm

Datasets FSRCNN SRGAN ESRGAN Ours
Set5 0.8657 0.8657 0.8569 0.6895
Set14 0.7564 0.7369 0.8697 0.7698
Bsd100 0.7156 0.6689 0.6783 0.6856
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
4 Hefte pro Jahr
Fachgebiete der Zeitschrift:
Informatik, Informatik, andere
Zeitschrift RSS Feed