Table 6 Quality parameters for leaf count.
From: A CNN-based model to count the leaves of rosette plants (LC-Net)
Sl. | Parameters | Remarks |
|---|---|---|
1 | Mean Square Error (MSE) | It’s calculated by taking the mean of the squares of the errors - i.e., differences between the predicated leaf number and the ground truth. Lower value indicates better results. |
2 | Absolute DiC (Difference in count) | The calculation involves determining the average value of the absolute differences between the predicted leaf number and the actual leaf number. Lower value indicates better results. |
3 | Coefficient of determination (\(R^2\)) | It measures how well the predicted values match the ground truth. High value indicates better results. |
4 | Percentage agreement | It takes the percentage of how many times the predicted value is exactly same as ground truth. High value indicates better results. |
