Table 3 Features set non-polished class.

From: Texture-based image analysis and explainable machine learning for polished asphalt identification in pavement condition monitoring

Class

Sample

ᶿ

Contrast

Correlation

Dissimilarity

Energy

Homogeneity

ASM

0

0

131.41

0.860

8.13

0.021

0.135

0.000461

45°

210.10

0.776

10.45

0.019

0.106

0.000365

90°

122.92

0.869

7.92

0.021

0.140

0.000462

135°

131.41

0.860

8.13

0.021

0.135

0.000461

0

1

399.38

0.787

14.61

0.013

0.078

0.00017

45°

646.98

0.655

18.85

0.011

0.058

0.000139

90°

346.55

0.815

13.63

0.013

0.082

0.00018

135°

399.38

0.787

14.61

0.013

0.078

0.00017

0

.

.

.

.

.

.

.

.

.

.

45°

.

.

.

.

.

.

90°

.

.

.

.

.

.

135°

.

.

.

.

.

.

0

6239

288.30

0.774

12.583

0.015

0.088

0.000237

45°

471.78

0.629

16.323

0.013

0.068

0.000193

90°

233.82

0.816

11.454

0.015

0.095

0.000255

135°

288.30

0.774

12.583

0.0154

0.088

0.000237