Codesota · Computer Vision · Optical Character Recognition · inverse-textTasks/Computer Vision/Optical Character Recognition
Optical Character Recognition · benchmark dataset · 2020 · EN

inverse-text.

Dataset from Papers With Code

Submit a result ↵
§ 01 · Leaderboard

Best published scores.

34 results indexed across 2 metrics. Shaded row marks current SOTA; ties broken by submission date.

Primary
accuracy · higher is better
All metrics
f-measure-full-lexicon, f-measure-no-lexicon
f-measure-full-lexicon
17 rows
#ModelOrgSubmittedPaper / codef-measure-full-lexicon
01OmniParserAlibabaMar 2024arxiv88.90
02DNTextSpotter (ViTAEv2-S)AcademicAug 2024arxiv83.80
03LRANet++AcademicNov 2025arxiv83.50
04LSGSpotterAcademicDec 2024arxiv82.30
05DNTextSpotter (ResNet-50)AcademicAug 2024arxiv81.60
06IASTAcademicJan 2024arxiv80.60
07SwinTextSpotter v2AcademicJan 2025arxiv76.50
08DeepSolo (ViTAEv2-S, TextOCR)—May 2023DeepSolo++: Let Transformer Decoder with Explicit Points… · code75.80
09SPTS v2—Jan 2025arxiv74.90
10DeepSolo (ResNet-50, TextOCR)—May 2023DeepSolo++: Let Transformer Decoder with Explicit Points… · code71.20
11SwinTextSpotter—Mar 2022SwinTextSpotter: Scene Text Spotting via Better Synergy … · code67.90
12DeepSolo (ResNet-50)—May 2023DeepSolo++: Let Transformer Decoder with Explicit Points… · code53.90
13ABCNet v2—May 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time E… · code47.40
14SPTS—Dec 2021SPTS: Single-Point Text Spotting · code46.20
15MaskTextSpotter v2—Jul 2018Mask TextSpotter: An End-to-End Trainable Neural Network… · code43.50
16TESTR—Apr 2022Text Spotting Transformers · code41.60
17ABCNet—Feb 2020ABCNet: Real-time Scene Text Spotting with Adaptive Bezi… · code34.30
f-measure-no-lexicon
17 rows
#ModelOrgSubmittedPaper / codef-measure-no-lexicon
01OmniParserAlibabaMar 2024arxiv84
02DNTextSpotter (ViTAEv2-S)AcademicAug 2024arxiv78.10
03DNTextSpotter (ResNet-50)AcademicAug 2024arxiv75.90
04LRANet++AcademicNov 2025arxiv75.30
05LSGSpotterAcademicDec 2024arxiv73.70
06DeepSolo (ViTAEv2-S, TextOCR)—May 2023DeepSolo++: Let Transformer Decoder with Explicit Points… · code68.80
07IASTAcademicJan 2024arxiv68.80
08SwinTextSpotter v2AcademicJan 2025arxiv64.80
09DeepSolo (ResNet-50, TextOCR)—May 2023DeepSolo++: Let Transformer Decoder with Explicit Points… · code64.60
10SPTS v2—Jan 2025arxiv63.40
11SwinTextSpotter—Mar 2022SwinTextSpotter: Scene Text Spotting via Better Synergy … · code55.40
12DeepSolo (ResNet-50)—May 2023DeepSolo++: Let Transformer Decoder with Explicit Points… · code48.50
13MaskTextSpotter v2—Jul 2018Mask TextSpotter: An End-to-End Trainable Neural Network… · code39
14SPTS—Dec 2021SPTS: Single-Point Text Spotting · code38.30
15ABCNet v2—May 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time E… · code34.50
16TESTR—Apr 2022Text Spotting Transformers · code34.20
17ABCNet—Feb 2020ABCNet: Real-time Scene Text Spotting with Adaptive Bezi… · code22.20
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 04 · Literature

7 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies