Codesota · Computer Vision · Optical Character Recognition · read2016(line-level)Tasks/Computer Vision/Optical Character Recognition
Optical Character Recognition · benchmark dataset · 2020 · EN

read2016(line-level).

Dataset from Papers With Code

Submit a result
§ 01 · Leaderboard

Best published scores.

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


Primary
accuracy · higher is better
All metrics
test-cer, test-wer
test-cer
6 rows
#ModelOrgSubmittedPaper / codetest-cer
01HTR-ConvTextDAIR-GroupDec 2024HTR-ConvText: Leveraging Convolution and Textual Informa…3.60
02HTR-VTSep 2024HTR-VT: Handwritten Text Recognition with Vision Transfo… · code3.90
03VANDec 2020End-to-end Handwritten Paragraph Text Recognition Using … · code4.10
04DANMar 2022DAN: a Segmentation-free Document Attention Network for … · code4.10
05SpanFeb 2021SPAN: a Simple Predict & Align Network for Handwritten P… · code4.60
06CNN + BLSTMMar 2019Evaluating Sequence-to-Sequence Models for Handwritten T… · code4.70
test-wer
5 rows
#ModelOrgSubmittedPaper / codetest-wer
01HTR-ConvTextDAIR-GroupDec 2024HTR-ConvText: Leveraging Convolution and Textual Informa…15.70
02VANDec 2020End-to-end Handwritten Paragraph Text Recognition Using … · code16.30
03HTR-VTSep 2024HTR-VT: Handwritten Text Recognition with Vision Transfo… · code16.50
04DANMar 2022DAN: a Segmentation-free Document Attention Network for … · code17.60
05SpanFeb 2021SPAN: a Simple Predict & Align Network for Handwritten P… · code21.10
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

6 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