{"url":"/dataset/scut-ctw1500","name":"SCUT-CTW1500","full_name":null,"description_markdown":"The **SCUT-CTW1500** dataset contains 1,500 images: 1,000 for training and 500 for testing. In particular, it provides 10,751 cropped text instance images, including 3,530 with curved text. The images are manually harvested from the Internet, image libraries such as Google Open-Image, or phone cameras. The dataset contains a lot of horizontal and multi-oriented text.\r\n\r\nSource: [Text Recognition in the Wild: A Survey](https://arxiv.org/abs/2005.03492)\r\nImage Source: [https://github.com/Yuliang-Liu/Curve-Text-Detector](https://github.com/Yuliang-Liu/Curve-Text-Detector)","description_withheld":null,"homepage":"https://github.com/Yuliang-Liu/Curve-Text-Detector","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/detecting-curve-text-in-the-wild-new-dataset","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","first_author":"Liu Yuliang","url":null},"license":{"name":"Custom (research-only)","url":"https://github.com/Yuliang-Liu/Curve-Text-Detector"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Scene Text Detection","url":"/task/scene-text-detection","datasets_with_task":"/datasets/task/scene-text-detection"},{"name":"Text Spotting","url":"/task/text-spotting","datasets_with_task":"/datasets/task/text-spotting"},{"name":"Curved Text Detection","url":"/task/curved-text-detection","datasets_with_task":"/datasets/task/curved-text-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["SCUT-CTW1500"],"data_loaders":[{"repo":"https://github.com/open-mmlab/mmocr","url":"https://github.com/open-mmlab/mmocr/blob/main/docs/datasets.md","frameworks":["pytorch"]},{"repo":"https://github.com/Yuliang-Liu/Curve-Text-Detector","url":"https://github.com/Yuliang-Liu/Curve-Text-Detector","frameworks":["pytorch"]}],"num_papers_in_archive":44,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/scene-text-detection-on-scut-ctw1500","task":"Scene Text Detection","dataset_variant":"SCUT-CTW1500","rows":17,"metrics":["F-Measure","Precision","Recall","FPS"],"first_row_in_archive_order":{"model":"MixNet","paper":"/paper/mixnet-toward-accurate-detection-of","metrics":{"F-Measure":"89.8","FPS":"15.2","Precision":"91.4","Recall":"88.3"},"code_links":[{"title":"D641593/MixNet","url":"https://github.com/D641593/MixNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-spotting-on-scut-ctw1500","task":"Text Spotting","dataset_variant":"SCUT-CTW1500","rows":11,"metrics":["F-measure (%) - No Lexicon","F-Measure (%) - Full Lexicon"],"first_row_in_archive_order":{"model":"A3S","paper":"/paper/a3s-adversarial-learning-of-semantic","metrics":{"F-Measure (%) - Full Lexicon":"82.3","F-measure (%) - No Lexicon":"64.4"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/curved-text-detection-on-scut-ctw1500","task":"Curved Text Detection","dataset_variant":"SCUT-CTW1500","rows":5,"metrics":["F-Measure"],"first_row_in_archive_order":{"model":"TextCohesion","paper":"/paper/190412640","metrics":{"F-Measure":"86.3%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mixnet-toward-accurate-detection-of","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","date":"2023-08-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/srformer-empowering-regression-based-text","title":"SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression","date":"2023-08-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deepsolo-let-transformer-decoder-with-1","title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","date":"2023-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a3s-adversarial-learning-of-semantic","title":"A3S: Adversarial learning of semantic representations for Scene-Text Spotting","date":"2023-02-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/abinet-autonomous-bidirectional-and-iterative","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","date":"2022-11-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dptext-detr-towards-better-scene-text","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","date":"2022-07-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/text-spotting-transformers","title":"Text Spotting Transformers","date":"2022-04-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":7,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/swintextspotter-scene-text-spotting-via","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","date":"2022-03-19","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spts-single-point-text-spotting","title":"SPTS: Single-Point Text Spotting","date":"2021-12-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fast-searching-for-a-faster-arbitrarily","title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","date":"2021-11-03","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/tpsnet-thin-plate-spline-representation-for","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","date":"2021-10-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/i3cl-intra-and-inter-instance-collaborative","title":"I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection","date":"2021-08-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/abcnet-v2-adaptive-bezier-curve-network-for","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","date":"2021-05-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mango-a-mask-attention-guided-one-stage-scene","title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","date":"2020-12-08","rows_on_this_dataset":1,"code_links":1,"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/text-perceptron-towards-end-to-end-arbitrary","title":"Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting","date":"2020-02-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-time-scene-text-detection-with","title":"Real-time Scene Text Detection with Differentiable Binarization","date":"2019-11-20","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":25,"samples_ran":3,"samples_unverified":22,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/textdragon-an-end-to-end-framework-for","title":"TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting","date":"2019-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficient-and-accurate-arbitrary-shaped-text","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","date":"2019-08-16","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":28,"samples_ran":4,"samples_unverified":24,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190412640","title":"TextCohesion: Detecting Text for Arbitrary Shapes","date":"2019-04-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/shape-robust-text-detection-with-progressive-1","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","date":"2019-03-28","rows_on_this_dataset":1,"code_links":19,"syntology":null},{"paper":"/paper/mask-r-cnn-with-pyramid-attention-network-for","title":"Mask R-CNN with Pyramid Attention Network for Scene Text Detection","date":"2018-11-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/textsnake-a-flexible-representation-for","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","date":"2018-07-04","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/shape-robust-text-detection-with-progressive","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","date":"2018-06-07","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":5,"samples_unverified":19,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sliding-line-point-regression-for-shape","title":"Sliding Line Point Regression for Shape Robust Scene Text Detection","date":"2018-01-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/detecting-curve-text-in-the-wild-new-dataset","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","date":"2017-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-deconvolution-network-for-semantic","title":"Learning Deconvolution Network for Semantic Segmentation","date":"2015-05-17","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":8,"samples_harvested":142,"samples_ran":31,"samples_unverified":111,"pointer_only_for_licence":13,"papers_with_no_sample_that_ran":0,"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."}