Table 1 Text-line detection (text detection) performance comparison with Recall (%), Precision (%), and F1-measure (%) on three datasets of web videos
From: Chinese text-line detection from web videos with fully convolutional networks
Method | Dataset I | Dataset II | Dataset III | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Â | Precision | Recall | F1 | Precision | Recall | F1 | Precision | Recall | F1 |
Yin et al. | 88.24 | 82.28 | 85.15 | 86.71 | 83.73 | 85.19 | 86.42 | 82.67 | 84.50 |
Ours+ResNet-50 | 87.79 | 88.32 | 87.46 | 86.63 | 89.51 | 88.05 | 86.11 | 89.03 | 87.54 |
Ours+PVANET | 86.13 | 92.85 | 89.36 | 87.31 | 92.62 | 89.88 | 85.11 | 91.70 | 88.28 |