| HoText_v1 | 88.89% | 100.00% | 94.12% |
| gts-1000-minsize_1440-th_0.4 | 77.78% | 87.50% | 82.35% |
 Deep2Text II-2 | 66.67% | 100.00% | 80.00% |
| Deep2Text II+ | 66.67% | 100.00% | 80.00% |
| gts-1000-minsize_1300 | 66.67% | 85.71% | 75.00% |
| Deep2Text I | 55.56% | 100.00% | 71.43% |
| AdelaideMachineLearning | 55.56% | 100.00% | 71.43% |
| SRC-B-TextProcessingLab | 66.67% | 75.00% | 70.59% |
| SRC-B-MachineLearningLab | 66.67% | 75.00% | 70.59% |
| AIX Lab., LG Electronics | 66.67% | 75.00% | 70.59% |
| gts-1000-th_0.4 | 66.67% | 75.00% | 70.59% |
| HUST_MCLAB | 55.56% | 83.33% | 66.67% |
| Yunos_Robot1.0 | 55.56% | 83.33% | 66.67% |
| TextBoxes++ | 55.56% | 83.33% | 66.67% |
| FOTS | 55.56% | 83.33% | 66.67% |
| StradVision-1 | 55.56% | 71.43% | 62.50% |
| Beam search CUNI (decoding for TextSpotter - no postprocessing) | 55.56% | 71.43% | 62.50% |
| Adelaide_ConvLSTMs | 55.56% | 71.43% | 62.50% |
| Baseline OpenCV 3.0 + Tesseract | 44.44% | 66.67% | 53.33% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
| Beam search CUNI +S (decoding for TextSpotter - spell checked) | 0.00% | 0.00% | 0.00% |