Skip to main content

Table 20 Pavia University Confusion Matrix numeric values for PCA 30 CEU-Net no patching with a 75%/25% Training/Testing split

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

 

Asphalt

Meadows

Gravel

Trees

Painted metal sheets

Bare Soil

Bitumen

Self-Blocking Bricks

Shadows

Asphalt

1607

0

10

0

0

0

43

33

0

Meadows

0

4594

0

4

0

31

0

0

0

Gravel

2

1

448

0

0

0

0

99

0

Trees

0

33

0

681

0

1

0

0

0

Painted metal sheets

0

0

0

0

331

0

0

0

0

Bare Soil

0

76

0

2

0

1235

0

0

0

Bitumen

26

0

0

0

0

0

313

2

0

Self-Blocking Bricks

11

2

32

0

0

5

2

830

0

Shadows

0

0

0

0

0

0

0

0

240

  1. Highest performing values are highlighted in bold