Accesso libero

Super-resolution Reconstruction Based on Capsule Generative Adversarial Network

Ziyi Wu

Ziyi Wu

School of Computer Science and Engineering, Xi’an Technological Universityxi’an, China
Cerca questo autore su
Sciendo|Google Scholar
Wu, Ziyi
, 
Hongge Yao

Hongge Yao

School of Computer Science and Engineering, Xi’an Technological Universityxi’an, China
Cerca questo autore su
Sciendo|Google Scholar
Yao, Hongge
, 
Hualong Yang

Hualong Yang

School of Computer Science and Engineering, Xi’an Technological Universityxi’an, China
Cerca questo autore su
Sciendo|Google Scholar
Yang, Hualong
, 
Hong Jiang

Hong Jiang

School of Computer Science and Engineering, Xi’an Technological Universityxi’an, China
Cerca questo autore su
Sciendo|Google Scholar
Jiang, Hong
, 
Wei Zhang

Wei Zhang

School of Computer Science and Engineering, Xi’an Technological UniversityXi’an, China
Cerca questo autore su
Sciendo|Google Scholar
Zhang, Wei
 e 
Jun Yu

Jun Yu

School of Computer Science and Engineering, Xi’an Technological Universityxi’an, China
Cerca questo autore su
Sciendo|Google Scholar
Yu, Jun
  
26 mag 2023
Super-resolution Reconstruction Based on Capsule Generative Adversarial Network's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Pubblicato online: 26 mag 2023
Pagine: 69 - 81
DOI: https://doi.org/10.2478/ijanmc-2022-0038
Parole chiave
© 2022 Ziyi Wu et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Structure diagram of CSRGAN.
Structure diagram of CSRGAN.

Figure 2.

Structure diagram of RDB.
Structure diagram of RDB.

Figure 3.

u is n 8-dimensional vectors obtained by encapsulating and flattening the data through the PrimaryCaps layer, v1 is a 16-dimensional digital capsule vector after a routing process and v2 is the 32-dimensional vector output at the end of the second routing process. wij is the fully connected weight matrix of the connected vector. The vectors u' and v' are the prediction vectors of u and v1 obtained through a linear hierarchical relationship, the subscripts i, j correspond to the number of vector u and the next layer vector v1, respectively. The parameter bij is the log prior probability from the lower capsule to the upper capsule. The parameter bij is the logarithmic prior probability from the low-level capsule to the high-level capsule and is used to update each cij correspondingly. cij is the coupling coefficient connecting the two layers' vectors before and after, representing the degree of correlation between the i-th vector of the previous layer and the j-th vector of the next layer. Squash is a linear rectification function, which normalizes the results obtained.
u is n 8-dimensional vectors obtained by encapsulating and flattening the data through the PrimaryCaps layer, v1 is a 16-dimensional digital capsule vector after a routing process and v2 is the 32-dimensional vector output at the end of the second routing process. wij is the fully connected weight matrix of the connected vector. The vectors u' and v' are the prediction vectors of u and v1 obtained through a linear hierarchical relationship, the subscripts i, j correspond to the number of vector u and the next layer vector v1, respectively. The parameter bij is the log prior probability from the lower capsule to the upper capsule. The parameter bij is the logarithmic prior probability from the low-level capsule to the high-level capsule and is used to update each cij correspondingly. cij is the coupling coefficient connecting the two layers' vectors before and after, representing the degree of correlation between the i-th vector of the previous layer and the j-th vector of the next layer. Squash is a linear rectification function, which normalizes the results obtained.

Figure 4.

Panda.
Panda.

Figure 5.

Rome.
Rome.

Figure 6.

Nut.
Nut.

Figure 7.

Train PSNR is evaluated on Set5.
Train PSNR is evaluated on Set5.

Figure 8.

The Roman Colosseum(a).
The Roman Colosseum(a).

Figure 9.

The Roman Colosseum(b).
The Roman Colosseum(b).

Figure 10.

castle(a).
castle(a).

Figure 11.

castle(b).
castle(b).

PSNR and SSIM

Method Bicubic SRCNN SRGAN RDN CSRGAN
PSNR 28.39 30.45 29.43 32.44 32.58
SSIM 0.8102 0. 8616 0.8477 0.8988 0.9003
Lingua:
Inglese
Frequenza di pubblicazione:
4 volte all'anno
Argomenti della rivista:
Informatica, Informatica, altro
Feed RSS della rivista