Acceso abierto

Rural Revitalization Perspective: Application of Visual Design Technology Based on Style Migration Algorithm in Packaging and Illustration Design of Agricultural Products in Hebei Province

 y   
24 mar 2025

Cite
Descargar portada

Figure 1.

GANILLA Working principle
GANILLA Working principle

Figure 2.

AdaIN, WCT and SAD principle effect comparison diagram
AdaIN, WCT and SAD principle effect comparison diagram

Figure 3.

Fast style transfer network design based on SAD
Fast style transfer network design based on SAD

Figure 4.

R channel color histogram
R channel color histogram

Figure 5.

G channel color histogram
G channel color histogram

Figure 6.

B channel color histogram
B channel color histogram

Figure 7.

Respondents’ pleasant perception of the illustrations under GANILLA
Respondents’ pleasant perception of the illustrations under GANILLA

Figure 8.

Respondents’ pleasant perception of the illustrations under CycleGAN
Respondents’ pleasant perception of the illustrations under CycleGAN

Figure 9.

The illustration satisfaction survey under GANILLA
The illustration satisfaction survey under GANILLA

Figure 10.

The illustration satisfaction survey under CycleGAN
The illustration satisfaction survey under CycleGAN

Comparison method RGB value statistics table

Graphics Part 1 Part 2 Part 3 Part 4 Manhattan distance
Image 1 (98,73,83) (156,103,84) (263,148,106) (284,251,196) -
CycleGAN (68,54,63) (127,87,65) (238,127,85) (262,232,173) 38.20
GANILLA (80,67,78) (139,98,82) (255,145,101) (279,245,188) 78.33
Image 2 (81,55,41) (128,96,88) (193,181,154) (247,250,238) -
CycleGAN (66,49,37) (117,89,80) (179,172,138) (226,227,205) 40.67
GANILLA (73,51,37) (119,92,86) (182,176,151) (235,241,230) 81.52

PSNR and SSIM values of GANILLA and CycleGAN

Method Image PSNR SSIM
CycleGAN a 7.254 -0.054
b 5.654 -0.088
c 9.587 -0.011
d 6.331 -0.107
GANILLA a 11.543 0.321
b 8.603 0.152
c 12.467 0.476
d 9.572 0.197