{"url":"/dataset/icdar-2013","name":"ICDAR 2013","full_name":null,"description_markdown":"The **ICDAR 2013** dataset consists of 229 training images and 233 testing images, with word-level annotations provided. It is the standard benchmark dataset for evaluating near-horizontal text detection.\r\n\r\nSource: [Single Shot Text Detector with Regional Attention](https://arxiv.org/abs/1709.00138)\r\nImage Source: [https://plos.figshare.com/articles/Detection_examples_of_the_proposed_method_on_the_ICDAR_2013_dataset_17_/5325856](https://plos.figshare.com/articles/Detection_examples_of_the_proposed_method_on_the_ICDAR_2013_dataset_17_/5325856)","description_withheld":null,"homepage":"https://rrc.cvc.uab.es/?ch=2","introduced_date":"2013-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"ICDAR 2013 Robust Reading Competition","first_author":null,"url":"https://doi.org/10.1109/ICDAR.2013.221"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Scene Text Recognition","url":"/task/scene-text-recognition","datasets_with_task":"/datasets/task/scene-text-recognition"},{"name":"Scene Text Detection","url":"/task/scene-text-detection","datasets_with_task":"/datasets/task/scene-text-detection"},{"name":"Table Detection","url":"/task/table-detection","datasets_with_task":"/datasets/task/table-detection"},{"name":"Handwritten Chinese Text Recognition","url":"/task/handwritten-chinese-text-recognition","datasets_with_task":"/datasets/task/handwritten-chinese-text-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ICDAR 2013","ICDAR2013"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/icdar-2013-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/mindee/doctr","url":"https://mindee.github.io/doctr/latest/datasets.html#doctr.datasets.IC13","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tanglang96/DataLoaders_DALI","url":"https://github.com/tanglang96/DataLoaders_DALI","frameworks":["pytorch"]}],"num_papers_in_archive":246,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","task":"Scene Text Recognition","dataset_variant":"ICDAR2013","rows":38,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CLIP4STR-L*","paper":"/paper/an-empirical-study-of-scaling-law-for-ocr","metrics":{"Accuracy":"99.42"},"code_links":[{"title":"large-ocr-model/large-ocr-model.github.io","url":"https://github.com/large-ocr-model/large-ocr-model.github.io"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset_variant":"ICDAR 2013","rows":16,"metrics":["F-Measure","Precision","Recall","H-Mean"],"first_row_in_archive_order":{"model":"TextFuseNet (ResNeXt-101)","paper":"/paper/textfusenet-scene-text-detection-with-richer","metrics":{"F-Measure":"94.61%","Precision":"97.27","Recall":"92.09"},"code_links":[{"title":"ying09/TextFuseNet","url":"https://github.com/ying09/TextFuseNet"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/textfusenet"},{"title":"kingcong/textfusenet","url":"https://github.com/kingcong/textfusenet"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/textfusenet"},{"title":"2023-MindSpore-1/ms-code-7","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/textfusenet"},{"title":"MindSpore-paper-code-2/code3","url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/textfusenet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/table-detection-on-icdar2013-1","task":"Table Detection","dataset_variant":"ICDAR2013","rows":3,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"cascadetabnet","paper":"/paper/cascadetabnet-an-approach-for-end-to-end","metrics":{"Avg F1":"1.0"},"code_links":[{"title":"DevashishPrasad/CascadeTabNet","url":"https://github.com/DevashishPrasad/CascadeTabNet"},{"title":"virtualsociety/ai-table-recognition","url":"https://github.com/virtualsociety/ai-table-recognition"},{"title":"hmnth1/table_ocr","url":"https://github.com/hmnth1/table_ocr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/an-empirical-study-of-scaling-law-for-ocr","title":"An Empirical Study of Scaling Law for OCR","date":"2023-12-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dtrocr-decoder-only-transformer-for-optical","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","date":"2023-08-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/diffusionstr-diffusion-model-for-scene-text","title":"DiffusionSTR: Diffusion Model for Scene Text Recognition","date":"2023-06-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/clip4str-a-simple-baseline-for-scene-text-1","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","date":"2023-05-23","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-supervised-character-to-character","title":"Self-supervised Character-to-Character Distillation for Text Recognition","date":"2022-11-01","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/multi-granularity-prediction-for-scene-text","title":"Multi-Granularity Prediction for Scene Text Recognition","date":"2022-09-08","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/scene-text-recognition-with-permuted","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","date":"2022-07-14","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/svtr-scene-text-recognition-with-a-single","title":"SVTR: Scene Text Recognition with a Single Visual Model","date":"2022-04-30","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/paper/a-glyph-driven-topology-enhancement-network","title":"Self-supervised Implicit Glyph Attention for Text Recognition","date":"2022-03-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/safl-a-self-attention-scene-text-recognizer-1","title":"SAFL: A Self-Attention Scene Text Recognizer with Focal Loss","date":"2022-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-semantics-allow-for-textual-reasoning-1","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","date":"2021-12-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-text-recognition-networks","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","date":"2021-11-30","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/cdistnet-perceiving-multi-domain-character","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","date":"2021-11-22","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/look-back-again-dual-parallel-attention","title":"Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition","date":"2021-08-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/why-you-should-try-the-real-data-for-the","title":"Why You Should Try the Real Data for the Scene Text Recognition","date":"2021-07-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/representation-and-correlation-enhanced","title":"Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition","date":"2021-06-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vision-transformer-for-fast-and-efficient","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","date":"2021-05-18","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/cstr-a-classification-perspective-on-scene","title":"Revisiting Classification Perspective on Scene Text Recognition","date":"2021-02-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cdec-net-composite-deformable-cascade-network","title":"CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images","date":"2020-08-25","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/seed-semantics-enhanced-encoder-decoder","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","date":"2020-05-22","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/textfusenet-scene-text-detection-with-richer","title":"TextFuseNet: Scene Text Detection with Richer Fused Features","date":"2020-05-17","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/cascadetabnet-an-approach-for-end-to-end","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","date":"2020-04-27","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-accurate-scene-text-recognition-with","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","date":"2020-03-27","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/tablenet-deep-learning-model-for-end-to-end","title":"TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images","date":"2020-01-06","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/textscanner-reading-characters-in-order-for","title":"TextScanner: Reading Characters in Order for Robust Scene Text Recognition","date":"2019-12-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/decoupled-attention-network-for-text","title":"Decoupled Attention Network for Text Recognition","date":"2019-12-21","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/on-recognizing-texts-of-arbitrary-shapes-with","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","date":"2019-10-10","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unsharp-masking-layer-injecting-prior","title":"Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification","date":"2019-09-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/what-is-wrong-with-scene-text-recognition","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","date":"2019-04-03","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":0,"samples_unverified":19,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/character-region-awareness-for-text-detection","title":"Character Region Awareness for Text Detection","date":"2019-04-03","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":40,"samples_ran":6,"samples_unverified":34,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scene-text-detection-with-supervised-pyramid","title":"Scene Text Detection with Supervised Pyramid Context Network","date":"2018-11-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/show-attend-and-read-a-simple-and-strong","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","date":"2018-11-02","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scene-text-recognition-from-two-dimensional","title":"Scene Text Recognition from Two-Dimensional Perspective","date":"2018-09-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mask-textspotter-an-end-to-end-trainable","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","date":"2018-07-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/aster-an-attentional-scene-text-recognizer","title":"ASTER: An Attentional Scene Text Recognizer with Flexible Rectification","date":"2018-06-25","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/detecting-multi-oriented-text-with-corner","title":"Detecting Multi-Oriented Text with Corner-based Region Proposals","date":"2018-04-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-oriented-scene-text-detection-via","title":"Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation","date":"2018-02-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textboxes-a-single-shot-oriented-scene-text","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","date":"2018-01-09","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pixellink-detecting-scene-text-via-instance","title":"PixelLink: Detecting Scene Text via Instance Segmentation","date":"2018-01-04","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/single-shot-text-detector-with-regional","title":"Single Shot Text Detector with Regional Attention","date":"2017-09-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/wordsup-exploiting-word-annotations-for","title":"WordSup: Exploiting Word Annotations for Character based Text Detection","date":"2017-08-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/stn-ocr-a-single-neural-network-for-text","title":"STN-OCR: A single Neural Network for Text Detection and Text Recognition","date":"2017-07-27","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/detecting-oriented-text-in-natural-images-by","title":"Detecting Oriented Text in Natural Images by Linking Segments","date":"2017-03-19","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/star-net-a-spatial-attention-residue-network","title":"Star-net: A spatial attention residue network for scene text recognition.","date":"2016-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/synthetic-data-for-text-localisation-in","title":"Synthetic Data for Text Localisation in Natural Images","date":"2016-04-22","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/robust-scene-text-recognition-with-automatic","title":"Robust Scene Text Recognition with Automatic Rectification","date":"2016-03-12","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/an-end-to-end-trainable-neural-network-for","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","date":"2015-07-21","rows_on_this_dataset":1,"code_links":85,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":81,"samples_ran":19,"samples_unverified":62,"pointer_only_for_licence":17,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-scene-text-localization-and","title":"Efficient Scene Text Localization and Recognition with Local Character Refinement","date":"2015-04-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reading-text-in-the-wild-with-convolutional","title":"Reading Text in the Wild with Convolutional Neural Networks","date":"2014-12-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/synthetic-data-and-artificial-neural-networks","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","date":"2014-06-09","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":11,"samples_harvested":183,"samples_ran":34,"samples_unverified":149,"pointer_only_for_licence":22,"papers_with_no_sample_that_ran":6,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}