{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/detecting-oriented-text-in-natural-images-by","title":"Detecting Oriented Text in Natural Images by Linking Segments","arxiv_id":"1703.06520","date":"2017-03-19","proceeding":"CVPR 2017 7","authors":["Baoguang Shi","Xiang Bai","Serge Belongie"],"abstract":"Most state-of-the-art text detection methods are specific to horizontal Latin\ntext and are not fast enough for real-time applications. We introduce Segment\nLinking (SegLink), an oriented text detection method. The main idea is to\ndecompose text into two locally detectable elements, namely segments and links.\nA segment is an oriented box covering a part of a word or text line; A link\nconnects two adjacent segments, indicating that they belong to the same word or\ntext line. Both elements are detected densely at multiple scales by an\nend-to-end trained, fully-convolutional neural network. Final detections are\nproduced by combining segments connected by links. Compared with previous\nmethods, SegLink improves along the dimensions of accuracy, speed, and ease of\ntraining. It achieves an f-measure of 75.0% on the standard ICDAR 2015\nIncidental (Challenge 4) benchmark, outperforming the previous best by a large\nmargin. It runs at over 20 FPS on 512x512 images. Moreover, without\nmodification, SegLink is able to detect long lines of non-Latin text, such as\nChinese.","url_abs":"http://arxiv.org/abs/1703.06520v3","url_pdf":"http://arxiv.org/pdf/1703.06520v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"detecting-oriented-text-in-natural-images-by","repo_url":"https://github.com/GuoLiuFang/seglink-lfs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"detecting-oriented-text-in-natural-images-by","repo_url":"https://github.com/Yiming992/Test-Linking-Segments-Text-Localization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"detecting-oriented-text-in-natural-images-by","repo_url":"https://github.com/YohannaYin/segmentlink_yh","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"detecting-oriented-text-in-natural-images-by","repo_url":"https://github.com/bgshih/seglink","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"detecting-oriented-text-in-natural-images-by","repo_url":"https://github.com/curbmap/curbmap-ml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"detecting-oriented-text-in-natural-images-by","repo_url":"https://github.com/dengdan/seglink","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"curved-text-detection","task_name":"Curved Text Detection"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset":"ICDAR 2013","model":"SegLink","rank_in_archive_order":11,"of":16,"metrics":{"F-Measure":"85.3%","Precision":"87.7","Recall":"83"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"WordSup (VGG16-synth-icdar)","rank_in_archive_order":38,"of":43,"metrics":{"F-Measure":"78.2","Precision":"79.3","Recall":"77.0"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-msra-td500","task":"Scene Text Detection","dataset":"MSRA-TD500","model":"SegLink","rank_in_archive_order":17,"of":18,"metrics":{"F-Measure":"77","Precision":"86","Recall":"70"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.06520","atlas_url":"https://app.syntology.ai/?focus=1703.06520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06520"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GuoLiuFang/seglink-lfs","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dengdan/seglink","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YohannaYin/segmentlink_yh","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/curbmap/curbmap-ml","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Yiming992/Test-Linking-Segments-Text-Localization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bgshih/seglink","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"4201fce83949ddcd","entry":"read_jpeg_check","repo":"YohannaYin/segmentlink_yh","repo_kind":"listed","path":"seglink/tool/create_datasets.py","file_url":"https://github.com/YohannaYin/segmentlink_yh/blob/HEAD/seglink/tool/create_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4201fce83949ddcd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}