Table 5.
KNN using GLCM features | Precision | Recall | F1-score |
---|---|---|---|
Clean | 0.76 | 0.76 | 0.76 |
Dirty | 0.83 | 0.80 | 0.81 |
Thin | 0.97 | 0.97 | 0.97 |
Thick | 0.91 | 0.95 | 0.93 |
Macro avg. | 0.87 | 0.87 | 0.87 |
Weighted avg. | 0.87 | 0.87 | 0.87 |
Average accuracy | 0.8695 |