Table 1.
Statistical evaluation of the accuracy, precision, and recall for object detection with YOLO, segmentation with u-net, and morphological image processing compared to the ground truth.
| YOLO | u-net | Morph. image proc. | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | Precision | Recall | Accuracy | Precision | Recall | Accuracy | Precision | Recall | |
| mean | 84.8 | 74.5 | 84.9 | 92.4 | 49.8 | 93.2 | 89.0 | 55.7 | 88.3 |
| std | 10.8 | 12.3 | 11.2 | 7.9 | 12.8 | 7.3 | 8.9 | 14.1 | 9.6 |
Notes. The values are given in percent. The highest mean value for accuracy, precision, and recall among the three methods is highlighted in bold.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.