Table 4 Calculation results of MS-SSIM evaluation index of image distortion degree detection experiment.

From: Research on the generation and annotation method of thin section images of tight oil reservoir based on deep learning

Algorithm

MS-SSIM/%

Quartz

Feldspar

Lithic

PP

CP

CDP

Microcrack

Overall

Average

CA-StyleGAN

97.33

96.34

97.29

96.52

95.56

95.89

96.38

96.34

96.47

StyleGAN

88.13

85.87

88.61

87.23

85.98

87.15

87.93

87.33

87.27

CycleGAN

88.64

86.02

89.1

88.28

86.35

87.96

88.17

87.84

87.79

DCGAN

92.5

90.33

92.68

91.85

90.03

91.97

92.02

91.79

91.63

WGAN-GP

83.85

80.95

84.2

83.55

81.41

83.09

83.15

82.69

82.89

LS-GAN

82.35

80.12

83.21

82.34

79.74

81.55

82.22

81.02

81.65

Back to article page