Table 1 Classification accuracies for fine grained taxonomy of fruits and vegetables.
From: Machine learning approaches for large scale classification of produce
Fruit Type | Number of Classes | Number of Samples | Visible | NIR 1 | NIR 2 | Composite |
|---|---|---|---|---|---|---|
(Organic/Inorganic) | (0–700 nm) | (700–1100 nm) | (1100–2000 nm) | (0–2000 nm) | ||
Apples | 8 | 13808 | 0.915 | 0.943 | 0.836 | 0.906 |
Strawberries | 2 | 980 | 0.828 | 0.84 | 0.917 | 0.942 |
Grapes | 2 | 947 | 0.973 | 0.906 | 0.867 | 0.921 |
Oranges | 4 | 2599 | 0.94 | 0.911 | 0.987 | 0.981 |
Mushrooms | 3 | 1217 | 0.99 | 0.99 | 0.941 | 0.943 |
Onions | 2 | 2686 | 0.99 | 0.99 | 0.892 | 0.903 |
Bell Peppers | 5 | 1483 | 0.975 | 0.959 | 0.954 | 0.945 |
Jalapeno Chilli | 3 | 3292 | 0.964 | 0.9 | 0.979 | 0.976 |
Potatoes | 3 | 5541 | 0.981 | 0.949 | 0.962 | 0.963 |
Tomatoes | 6 | 3718 | 0.945 | 0.906 | 0.876 | 0.902 |
