Skip to main content

Table 15 Detailed classification test results for the Kennedy Space Center Dataset in terms of Precision, Recall, and F1-Score. Testing was done with PCA 30 CEU-Net no-patching with a 75%/25% Training/Testing split

From: CEU-Net: ensemble semantic segmentation of hyperspectral images using clustering

Class Labels

Precision

Recall

f1-score

Support

Scrub

0.96

0.98

0.97

197

Willow Swamp

0.97

0.94

0.96

72

CP Hammock

0.84

0.90

0.87

63

Slash Pine

0.82

0.75

0.78

67

Oak/Broadleaf

0.85

0.79

0.82

43

Hardwood

0.89

0.85

0.87

47

Swamp

0.90

0.90

0.90

31

Graminoid Marsh

0.97

0.94

0.95

109

Spartina Marsh

0.95

1.00

0.97

135

Cattail Marsh

0.97

1.00

0.98

87

Salt Marsh

1.00

0.99

0.99

97

Mud Flats

0.99

0.97

0.98

121

Water

1.00

1.00

1.00

234

Accuracy

  

0.95

1303

Macro Average

0.93

0.92

0.93

1303

Weighted Average

0.95

0.95

0.95

1303