Table 5 Training and validation of optimal multiple linear regression model
From: Image analysis-based recognition and quantification of grain number per panicle in rice
Rice subspecies | Combination method | Training | Validation | |||
|---|---|---|---|---|---|---|
Models | R2 | RMSE | R2 | RMSE | ||
Indica | Scanner + Shape B | GN = 364.93 × CDʹ + 0.70 × Skʹ − 3.90 × Coʹ + 2.801 | 0.990 | 4.6732 | 0.980 | 6.3254 |
Scanner + Shape C | GN = 363.72 × CDʹ + 10.50 × Skʹ − 13.48 × Coʹ + 5.348 | 0.990 | 4.6345 | 0.980 | 6.3574 | |
Camera + Shape B | GN = 396.82 × CDʹ − 21.70 × Skʹ − 7.32 × Coʹ + 11.823 | 0.974 | 7.6989 | 0.965 | 8.3016 | |
Camera + Shape C | GN = 395.60 × CDʹ − 11.90 × Skʹ − 16.90 × Coʹ + 14.369 | 0.975 | 7.5595 | 0.964 | 8.3956 | |
Japonica | Scanner + Shape B | GN = 481.49 × CDʹ + 178.22 × Skʹ − 164.85 × Coʹ − 18.485 | 0.979 | 6.0957 | 0.975 | 6.4714 |
Scanner + Shape C | GN = 482.28 × CDʹ + 178.63 × Skʹ − 164.00 × Coʹ − 17.031 | 0.980 | 5.9838 | 0.976 | 6.4587 | |
Camera + Shape B | GN = 500.64 × CDʹ + 188.62 × Skʹ − 205.06 × Coʹ − 5.477 | 0.954 | 9.1121 | 0.953 | 8.5389 | |
Camera + Shape C | GN = 501.43 × CDʹ + 189.03 × Skʹ − 204.22 × Coʹ − 4.023 | 0.954 | 9.0961 | 0.953 | 8.5910 | |