Table 1.
Quantitative detection results on TotalText. “-”/ “✓” means without/within training data. “P”, “R”, and “F” represent the Precision, Recall, and F-measure, respectively.
| Method | Ext | P | R | F |
|---|---|---|---|---|
| EAST [8] | - | 80.9 | 76.2 | 78.5 |
| TextSnake [20] | ✓ | 82.7 | 74.5 | 78.4 |
| MSC [19] | ✓ | 83.8 | 74.8 | 79.0 |
| PSENet [7] | - | 84.0 | 78.0 | 80.9 |
| PAN [1] | - | 88.0 | 79.4 | 83.5 |
| TextRay [30] | - | 83.5 | 77.9 | 80.6 |
| SegLink++ [13] | ✓ | 82.1 | 80.9 | 81.5 |
| LOMO [14] | ✓ | 87.6 | 79.3 | 83.3 |
| SPCNet [40] | ✓ | 83.0 | 82.8 | 82.9 |
| PCR [10] | - | 86.4 | 81.5 | 83.9 |
| CRAFT [27] | ✓ | 87.6 | 79.9 | 83.6 |
| Ours_DenseTextPVT | - | 89.4 | 80.1 | 84.7 |