Optical Character Recognition2020en
inverse-text
Dataset from Papers With Code
Metrics:accuracy, cer, wer, f1
f-measure-full-lexicon
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | DeepSolo (ViTAEv2-S, TextOCR) | 75.8 | May 2023 | |
| 2 | DeepSolo (ResNet-50, TextOCR) | 71.2 | May 2023 | |
| 3 | SwinTextSpotter | 67.9 | Mar 2022 | |
| 4 | DeepSolo (ResNet-50) | 53.9 | May 2023 | |
| 5 | ABCNet v2 | 47.4 | May 2021 | |
| 6 | SPTS | 46.2 | Dec 2021 | |
| 7 | MaskTextSpotter v2 | 43.5 | Jul 2018 | |
| 8 | TESTR | 41.6 | Apr 2022 | |
| 9 | ABCNet | 34.3 | Feb 2020 |
f-measure-no-lexicon
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | DeepSolo (ViTAEv2-S, TextOCR) | 68.8 | May 2023 | |
| 2 | DeepSolo (ResNet-50, TextOCR) | 64.6 | May 2023 | |
| 3 | SwinTextSpotter | 55.4 | Mar 2022 | |
| 4 | DeepSolo (ResNet-50) | 48.5 | May 2023 | |
| 5 | MaskTextSpotter v2 | 39 | Jul 2018 | |
| 6 | SPTS | 38.3 | Dec 2021 | |
| 7 | ABCNet v2 | 34.5 | May 2021 | |
| 8 | TESTR | 34.2 | Apr 2022 | |
| 9 | ABCNet | 22.2 | Feb 2020 |
Related Papers7
DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
May 2023Models: DeepSolo (ViTAEv2-S, TextOCR), DeepSolo (ResNet-50, TextOCR), DeepSolo (ResNet-50)
Text Spotting Transformers
Apr 2022Models: TESTR
SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
Mar 2022Models: SwinTextSpotter
SPTS: Single-Point Text Spotting
Dec 2021Models: SPTS
ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
May 2021Models: ABCNet v2
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
Feb 2020Models: ABCNet
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
Jul 2018Models: MaskTextSpotter v2