method: CLOVA-AI / PAPAGO2018-08-01
Authors: Sunghyo Chung, Youngmin Baek, Hwalsuk Lee, Jaegul Choo
Description: We formulate script identification as a semantic segmentation task. We use both MLT task1 and task2 datasets for training. CLOVA-AI team, Naver Corp.
Confusion Matrix
| Detection | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Arabic | Latin | Chinese | Japanese | Korean | Bangla | Symbols | Mixed | None | ||
| GT | Arabic | 4516 | 571 | 3 | 17 | 15 | 8 | 12 | 0 | 0 |
| Latin | 103 | 59222 | 261 | 478 | 261 | 39 | 173 | 0 | 0 | |
| Chinese | 10 | 362 | 3497 | 823 | 41 | 5 | 12 | 0 | 0 | |
| Japanese | 35 | 1812 | 1091 | 4977 | 209 | 7 | 26 | 0 | 0 | |
| Korean | 15 | 1801 | 265 | 553 | 10328 | 18 | 12 | 0 | 0 | |
| Bangla | 5 | 303 | 20 | 18 | 18 | 2180 | 1 | 0 | 0 | |
| Symbols | 14 | 1272 | 3 | 30 | 6 | 4 | 2167 | 0 | 0 | |
| Mixed | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | |
| None | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | |