| TextFuseNet: Scene Text Detection with Richer Fused Features | ✓ Link | 92.23 | 93.96 | 90.56 | | | TextFuseNet (ResNeXt-101) | 2020-05-17 |
| Convolutional Character Networks | ✓ Link | 91.55 | 92.65 | 90.47 | | | CharNet H-88 (multi-scale) | 2019-10-17 |
| Convolutional Character Networks | ✓ Link | 90.97 | 89.99 | 91.98 | | | CharNet H-88 (single-scale) | 2019-10-17 |
| Convolutional Character Networks | ✓ Link | 90.16 | 90.9 | 89.44 | | | CharNet H-50 (multi-scale) | 2019-10-17 |
| Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection | ✓ Link | 90.1 | 92.1 | 88.2 | | | SBD | 2019-12-20 |
| Convolutional Character Networks | ✓ Link | 90.06 | 91.43 | 88.74 | | | CharNet H-57 (multi-scale) | 2019-10-17 |
| FOTS: Fast Oriented Text Spotting with a Unified Network | ✓ Link | 89.84 | 91.85 | 87.92 | | | FOTS MS | 2018-01-05 |
| Convolutional Character Networks | ✓ Link | 89.7 | 91.15 | 88.3 | | | CharNet H-50 (single-scale) | 2019-10-17 |
| Convolutional Character Networks | ✓ Link | 89.66 | 88.88 | 90.45 | | | CharNet H-57 (single-scale) | 2019-10-17 |
| Pyramid Mask Text Detector | ✓ Link | 89.33 | 91.3 | 87.43 | | | PMTD | 2019-03-28 |
| Geometry Normalization Networks for Accurate Scene Text Detection | ✓ Link | 88.52 | 90.41 | 86.71 | | | GNNets | 2019-09-02 |
| FOTS: Fast Oriented Text Spotting with a Unified Network | ✓ Link | 87.99 | 91 | 85.17 | | | FOTS | 2018-01-05 |
| Real-time Scene Text Detection with Differentiable Binarization | ✓ Link | 87.3 | 91.8 | 83.2 | | | DB-ResNet-50 (1152) | 2019-11-20 |
| Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion | ✓ Link | 87.3 | 90.9 | 83.9 | | 10 | DBNet++ (ResNet-50) (1152) | 2022-02-21 |
| Scene Text Detection with Supervised Pyramid Context Network | ✓ Link | 87.2 | 88.7 | 85.8 | | | SPCNET | 2018-11-21 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 87.1 | 89.7 | 84.6 | | 15.7 | FAST-B-1280 | 2021-11-03 |
| Shape Robust Text Detection with Progressive Scale Expansion Network | ✓ Link | 87.1 | 88.7 | 85.5 | | | PSENet-1s | 2018-06-07 |
| A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning | ✓ Link | 86.91 | 86.72 | 87.09 | | | SAST | 2019-08-15 |
| Character Region Awareness for Text Detection | ✓ Link | 86.9 | 89.8 | 84.3 | | | CRAFT | 2019-04-03 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 86.3 | 89.2 | 83.6 | | 31.8 | FAST-B-896 | 2021-11-03 |
| Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes | ✓ Link | 86 | 91.6 | 81 | | | Mask TextSpotter | 2018-07-06 |
| Mask R-CNN with Pyramid Attention Network for Scene Text Detection | | 85.9 | 90.8 | 81.5 | | | PAN | 2018-11-22 |
| Shape Robust Text Detection with Progressive Scale Expansion Network | ✓ Link | 85.7 | 86.9 | 84.5 | | | PSENet-1s | 2019-03-28 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 84.7 | 88.0 | 81.7 | | 42.7 | FAST-B-736 | 2021-11-03 |
| Detecting Multi-Oriented Text with Corner-based Region Proposals | ✓ Link | 84.5 | 88.7 | 80.7 | | | Corner-based Region Proposals | 2018-04-08 |
| PixelLink: Detecting Scene Text via Instance Segmentation | ✓ Link | 84.5 | 85.5 | 83.6 | | | SLPR | 2018-01-04 |
| Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation | ✓ Link | 84.3 | 89.5 | 79.7 | | | Corner Localization (multi-scale) | 2018-02-25 |
| Fused Text Segmentation Networks for Multi-oriented Scene Text Detection | | 84.1 | 88.6 | 80 | | | FTSN + MNMS | 2017-09-11 |
| TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes | ✓ Link | 83.7 | 85.5 | 82 | | | PixelLink+VGG16 2s | 2018-07-04 |
| Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion | ✓ Link | 83.1 | 90.1 | 77.2 | | 44 | DBNet++ (ResNet-18) (736) | 2022-02-21 |
| TextBoxes++: A Single-Shot Oriented Scene Text Detector | ✓ Link | 82.9 | 87.8 | 78.5 | | | Quad_MS | 2018-01-09 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 82.9 | 86.3 | 79.8 | | 53.9 | FAST-S-736 | 2021-11-03 |
| EAST: An Efficient and Accurate Scene Text Detector | ✓ Link | 82.9 | 84 | 81.9 | | | PAN | 2017-04-11 |
| Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network | ✓ Link | 82.6 | 84.9 | 80.4 | | | TextSnake | 2019-08-16 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 81.7 | 86 | 77.9 | | 60.9 | FAST-T-736 | 2021-11-03 |
| Single Shot Text Detector with Regional Attention | ✓ Link | 80.7 | 83.3 | 78.3 | | | EAST + PVANET2x RBOX (multi-scale) | 2017-09-01 |
| EAST: An Efficient and Accurate Scene Text Detector | ✓ Link | 78.2 | 83.6 | 73.5 | | | EAST + PVANET2x RBOX (single-scale) | 2017-04-11 |
| Detecting Oriented Text in Natural Images by Linking Segments | ✓ Link | 78.2 | 79.3 | 77.0 | | | WordSup (VGG16-synth-icdar) | 2017-03-19 |
| WordSup: Exploiting Word Annotations for Character based Text Detection | | 77 | 80 | 73 | | | SSTD | 2017-08-22 |
| Multi-Oriented Text Detection with Fully Convolutional Networks | ✓ Link | 75 | 73.1 | 76.8 | | | SegLink | 2016-04-14 |
| PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network | ✓ Link | 53.6 | 70.8 | 43.0 | | | MCLAB_FCN | 2021-04-12 |
| PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network | ✓ Link | | | | 62.3 | | PGNet-A | 2021-04-12 |
| []() | | | | | 57.4 | | PGNet-E | |