{"url":"/sota/scene-text-detection-on-icdar-2017-mlt-1","task":{"name":"Scene Text Detection","url":"/task/scene-text-detection","note":null},"dataset":{"name":"ICDAR 2017 MLT","url":"/dataset/icdar-2017"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Scene Text Detection** is a computer vision task that involves automatically identifying and localizing text within natural images or videos. The goal of scene text detection is to develop algorithms that can robustly detect and and label text with bounding boxes in uncontrolled and complex environments, such as street signs, billboards, or license plates.\r\n\r\n\r\n<span class=\"description-source\">Source: [ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection ](https://arxiv.org/abs/2004.04940)</span>","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":["Precision","Recall","F-Measure","H-Mean"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Precision":"higher","Recall":"higher","F-Measure":null,"H-Mean":null}},"counts":{"rows":14,"rows_with_code":13,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PMTD*","metrics":{"F-Measure":"80.13%","Precision":"84.42","Recall":"76.25"},"uses_additional_data":false,"paper_date":"2019-03-28","paper":"/paper/pyramid-mask-text-detector","paper_url":"http://arxiv.org/abs/1903.11800v1","paper_title":"Pyramid Mask Text Detector","code":"https://github.com/jjprincess/PMTD","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"Corner Localization (single-scale)","metrics":{"F-Measure":"66.8%","Precision":"83.8","Recall":"55.6"},"uses_additional_data":false,"paper_date":"2018-02-25","paper":"/paper/multi-oriented-scene-text-detection-via","paper_url":"http://arxiv.org/abs/1802.08948v2","paper_title":"Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation","code":"https://github.com/lvpengyuan/corner","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"SBD","metrics":{"F-Measure":"79.47%","Precision":"82.75","Recall":"76.44"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/191209629","paper_url":"https://arxiv.org/abs/1912.09629v3","paper_title":"Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection","code":"https://github.com/Yuliang-Liu/Box_Discretization_Network","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"FOTS MS","metrics":{"F-Measure":"70.75%","Precision":"81.86","Recall":"62.3"},"uses_additional_data":false,"paper_date":"2018-01-05","paper":"/paper/fots-fast-oriented-text-spotting-with-a","paper_url":"http://arxiv.org/abs/1801.01671v2","paper_title":"FOTS: Fast Oriented Text Spotting with a Unified Network","code":"https://github.com/jiangxiluning/FOTS.PyTorch","n_code_links":7,"syntology":null},{"rank_in_archive_order":5,"model":"CharNet H-88","metrics":{"F-Measure":"75.77%","Precision":"81.27","Recall":"70.97"},"uses_additional_data":false,"paper_date":"2019-10-17","paper":"/paper/convolutional-character-networks","paper_url":"https://arxiv.org/abs/1910.07954v1","paper_title":"Convolutional Character Networks","code":"https://github.com/MalongTech/research-charnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"FOTS","metrics":{"F-Measure":"67.25%","Precision":"80.95","Recall":"57.51"},"uses_additional_data":false,"paper_date":"2018-01-05","paper":"/paper/fots-fast-oriented-text-spotting-with-a","paper_url":"http://arxiv.org/abs/1801.01671v2","paper_title":"FOTS: Fast Oriented Text Spotting with a Unified Network","code":"https://github.com/jiangxiluning/FOTS.PyTorch","n_code_links":7,"syntology":null},{"rank_in_archive_order":7,"model":"SPCNET","metrics":{"F-Measure":"74.1%","Precision":"80.6","Recall":"68.6"},"uses_additional_data":false,"paper_date":"2018-11-21","paper":"/paper/scene-text-detection-with-supervised-pyramid","paper_url":"http://arxiv.org/abs/1811.08605v1","paper_title":"Scene Text Detection with Supervised Pyramid Context Network","code":"https://github.com/AirBernard/Scene-Text-Detection-with-SPCNET","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"CRAFT","metrics":{"H-Mean":"73.9","Precision":"80.6","Recall":"68.2"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/character-region-awareness-for-text-detection","paper_url":"http://arxiv.org/abs/1904.01941v1","paper_title":"Character Region Awareness for Text Detection","code":"https://github.com/JaidedAI/EasyOCR","n_code_links":18,"syntology":{"n_ran":25,"n_unverified":15,"n_samples":40,"n_pointer_only_licence":4}},{"rank_in_archive_order":9,"model":"PAN","metrics":{"F-Measure":"74.3%","Precision":"80","Recall":"69.8"},"uses_additional_data":false,"paper_date":"2018-11-22","paper":"/paper/mask-r-cnn-with-pyramid-attention-network-for","paper_url":"http://arxiv.org/abs/1811.09058v1","paper_title":"Mask R-CNN with Pyramid Attention Network for Scene Text Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"GNNets","metrics":{"F-Measure":"74.54%","Precision":"79.63","Recall":"70.06"},"uses_additional_data":false,"paper_date":"2019-09-02","paper":"/paper/geometry-normalization-networks-for-accurate","paper_url":"https://arxiv.org/abs/1909.00794v1","paper_title":"Geometry Normalization Networks for Accurate Scene Text Detection","code":"https://github.com/bigvideoresearch/GNNets","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"CharNet R-50","metrics":{"F-Measure":"73.42%","Precision":"77.07","Recall":"70.1"},"uses_additional_data":false,"paper_date":"2019-10-17","paper":"/paper/convolutional-character-networks","paper_url":"https://arxiv.org/abs/1910.07954v1","paper_title":"Convolutional Character Networks","code":"https://github.com/MalongTech/research-charnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"PSENet-1s","metrics":{"F-Measure":"72.45%","Precision":"77.01","Recall":"68.4"},"uses_additional_data":false,"paper_date":"2018-06-07","paper":"/paper/shape-robust-text-detection-with-progressive","paper_url":"http://arxiv.org/abs/1806.02559v1","paper_title":"Shape Robust Text Detection with Progressive Scale Expansion Network","code":"https://github.com/whai362/PSENet","n_code_links":9,"syntology":{"n_ran":5,"n_unverified":19,"n_samples":24,"n_pointer_only_licence":2}},{"rank_in_archive_order":13,"model":"PSENet (ResNet-152)","metrics":{"F-Measure":"72.13%","Precision":"75.35","Recall":"69.18"},"uses_additional_data":false,"paper_date":"2019-03-28","paper":"/paper/shape-robust-text-detection-with-progressive-1","paper_url":"https://arxiv.org/abs/1903.12473v2","paper_title":"Shape Robust Text Detection with Progressive Scale Expansion Network","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":19,"syntology":null},{"rank_in_archive_order":14,"model":"Corner Localization (multi-scale)","metrics":{"F-Measure":"72.4%","Precision":"74.3","Recall":"70.6"},"uses_additional_data":false,"paper_date":"2018-02-25","paper":"/paper/multi-oriented-scene-text-detection-via","paper_url":"http://arxiv.org/abs/1802.08948v2","paper_title":"Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation","code":"https://github.com/lvpengyuan/corner","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":30,"n_unverified":34,"n_samples":64,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":30,"n_unverified":34,"n_samples":64,"n_pointer_only_licence":6,"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"}}}