Table 2. Redundant SG recognition by distinct prototypes.
Prototype | I | II | III | IV | V | VI | VII | VIII |
I | 41 | |||||||
II | 9 | 27 | ||||||
III | 3 | 2 | 21 | |||||
IV | 1 | 2 | 5 | 20 | ||||
V | 6 | 3 | 7 | 5 | 17 | |||
VI | 0 | 2 | 2 | 2 | 2 | 9 | ||
VII | 3 | 1 | 3 | 4 | 2 | 1 | 8 | |
VIII | 2 | 0 | 1 | 2 | 2 | 1 | 3 | 6 |
The percentage of SGs recognized by each prototype, or simultaneously by pairs of prototypes in the 6 representative micrographs of the training set, with a total of 282 granules is indicated. ST was 0.89 for prototype I; 0.88 for prototype II; 0.8 for prototype III; 0.88 for prototype IV; 0.86 for prototype V; 0.86 for prototype VI; 0.92 for prototype VII; and 0.85 for prototype VIII. Redundancy allowed a single SG to be recognized by multiple prototypes.