Table 3 Performance comparison of HSICNet with traditional classifiers (SVM and Random Forest) on Indian Pines, Pavia University, and Salinas datasets.

From: HSICNet a novel deep learning architecture for hyperspectral image classification in remote sensing and environmental monitoring

Model

Dataset

OA (%)

AA (%)

κ

F1-score

SVM

Indian Pines

84.52

82.13

0.81

0.835

RF

Indian Pines

87.91

84.70

0.85

0.865

HSICNet

Indian Pines

98.63

97.42

0.98

0.976

SVM

Pavia University

90.12

88.60

0.88

0.892

RF

Pavia University

92.33

90.11

0.91

0.905

HSICNet

Pavia University

99.14

98.30

0.99

0.986

SVM

Salinas

88.75

87.49

0.86

0.872

RF

Salinas

91.04

89.77

0.89

0.893

HSICNet

Salinas

99.35

98.91

0.99

0.991

Back to article page