Table 4 Predicted allocation of root pixels to labelled radial classes from root centre (inner 0–0.1 mm) to root border (> 1.3 mm) based on their spectral characteristics using a decision tree model
From: Hyperspectral imaging: a novel approach for plant root phenotyping
Class labels (mm) | Predicted allocation to class (%) | |||||||
|---|---|---|---|---|---|---|---|---|
0–0.1 | 0.1–0.3 | 0.3–0.5 | 0.5–0.7 | 0.7–0.9 | 0.9–1.1 | 1.1–1.3 | > 1.3 | |
0–0.1 | 51.1 | 12.0 | 7.4 | 7.5 | 8.4 | 8.9 | 9.5 | 8.8 |
0.1–0.3 | 32.6 | 68.2 | 27.4 | 27.4 | 29.0 | 29.7 | 34.3 | 31.7 |
0.3–0.5 | 13.2 | 15.8 | 58.4 | 26.2 | 28.0 | 29.7 | 26.6 | 31.1 |
0.5–0.7 | 2.8 | 3.6 | 6.2 | 38.1 | 8.3 | 8.2 | 8.0 | 7.6 |
0.7–0.9 | 0.2 | 0.3 | 0.6 | 0.7 | 26.2 | 1.0 | 1.1 | 0.9 |
0.9–1.1 | 0.0 | 0.0 | 0.1 | 0.1 | 0.0 | 22.5 | 0.1 | 0.1 |
1.1–1.3 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 20.4 | 0.0 |
> 1.3 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 19.8 |
Percentage total pixels | 18.9 | 39.2 | 26.1 | 10.4 | 3.3 | 1.2 | 0.5 | 0.3 |