{"url":"/sota/optical-character-recognition-on-benchmarking","task":{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","note":null},"dataset":{"name":"Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study","url":null},"category":"Computer Vision","categories":["Computer Vision","Methodology","Natural Language Processing"],"category_note":null,"description":"**Optical Character Recognition** or **Optical Character Reader** (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo (for example the text on signs and billboards in a landscape photo, license plates in cars...) or from subtitle text superimposed on an image (for example: from a television broadcast)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy (%)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy (%)":"higher"}},"counts":{"rows":7,"rows_with_code":6,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DTrOCR","metrics":{"Accuracy (%)":"89.6"},"uses_additional_data":false,"paper_date":"2023-08-30","paper":"/paper/dtrocr-decoder-only-transformer-for-optical","paper_url":"https://arxiv.org/abs/2308.15996v1","paper_title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","code":"https://github.com/arvindrajan92/DTrOCR","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DTrOCR 105M","metrics":{"Accuracy (%)":"89.6"},"uses_additional_data":false,"paper_date":"2023-08-30","paper":"/paper/dtrocr-decoder-only-transformer-for-optical","paper_url":"https://arxiv.org/abs/2308.15996v1","paper_title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","code":"https://github.com/arvindrajan92/DTrOCR","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"MaskOCR-L","metrics":{"Accuracy (%)":"82.6"},"uses_additional_data":false,"paper_date":"2022-06-01","paper":"/paper/maskocr-text-recognition-with-masked-encoder","paper_url":"https://arxiv.org/abs/2206.00311v3","paper_title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"TransOCR","metrics":{"Accuracy (%)":"72.8"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/scene-text-telescope-text-focused-scene-image","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Chen_Scene_Text_Telescope_Text-Focused_Scene_Image_Super-Resolution_CVPR_2021_paper.html","paper_title":"Scene Text Telescope: Text-Focused Scene Image Super-Resolution","code":"https://github.com/FudanVI/FudanOCR/tree/main/scene-text-telescope","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"SRN","metrics":{"Accuracy (%)":"65.0"},"uses_additional_data":false,"paper_date":"2020-03-27","paper":"/paper/towards-accurate-scene-text-recognition-with","paper_url":"https://arxiv.org/abs/2003.12294v1","paper_title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":3,"syntology":null},{"rank_in_archive_order":6,"model":"MORAN","metrics":{"Accuracy (%)":"64.3"},"uses_additional_data":false,"paper_date":"2019-01-10","paper":"/paper/a-multi-object-rectified-attention-network","paper_url":"http://arxiv.org/abs/1901.03003v1","paper_title":"A Multi-Object Rectified Attention Network for Scene Text Recognition","code":"https://github.com/topdu/openocr","n_code_links":7,"syntology":null},{"rank_in_archive_order":7,"model":"SEED","metrics":{"Accuracy (%)":"61.2"},"uses_additional_data":false,"paper_date":"2020-05-22","paper":"/paper/seed-semantics-enhanced-encoder-decoder","paper_url":"https://arxiv.org/abs/2005.10977v1","paper_title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":3,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}