{"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/mask-textspotter-v3-segmentation-proposal","title":"Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting","arxiv_id":"2007.09482","date":"2020-07-18","proceeding":"ECCV 2020 8","authors":["Minghui Liao","Guan Pang","Jing Huang","Tal Hassner","Xiang Bai"],"abstract":"Recent end-to-end trainable methods for scene text spotting, integrating detection and recognition, showed much progress. However, most of the current arbitrary-shape scene text spotters use region proposal networks (RPN) to produce proposals. RPN relies heavily on manually designed anchors and its proposals are represented with axis-aligned rectangles. The former presents difficulties in handling text instances of extreme aspect ratios or irregular shapes, and the latter often includes multiple neighboring instances into a single proposal, in cases of densely oriented text. To tackle these problems, we propose Mask TextSpotter v3, an end-to-end trainable scene text spotter that adopts a Segmentation Proposal Network (SPN) instead of an RPN. Our SPN is anchor-free and gives accurate representations of arbitrary-shape proposals. It is therefore superior to RPN in detecting text instances of extreme aspect ratios or irregular shapes. Furthermore, the accurate proposals produced by SPN allow masked RoI features to be used for decoupling neighboring text instances. As a result, our Mask TextSpotter v3 can handle text instances of extreme aspect ratios or irregular shapes, and its recognition accuracy won't be affected by nearby text or background noise. Specifically, we outperform state-of-the-art methods by 21.9 percent on the Rotated ICDAR 2013 dataset (rotation robustness), 5.9 percent on the Total-Text dataset (shape robustness), and achieve state-of-the-art performance on the MSRA-TD500 dataset (aspect ratio robustness). Code is available at: https://github.com/MhLiao/MaskTextSpotterV3","url_abs":"https://arxiv.org/abs/2007.09482v1","url_pdf":"https://arxiv.org/pdf/2007.09482v1.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":"mask-textspotter-v3-segmentation-proposal","repo_url":"https://github.com/MhLiao/MaskTextSpotterV3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"text-spotting","task_name":"Text Spotting"}],"methods":[{"method_slug":"rpn","method_name":"RPN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-spotting-on-icdar-2015","task":"Text Spotting","dataset":"ICDAR 2015","model":"MaskTextSpotter v3","rank_in_archive_order":12,"of":18,"metrics":{"F-measure (%) - Generic Lexicon":"74.2","F-measure (%) - Strong Lexicon":"83.3","F-measure (%) - Weak Lexicon":"78.1"},"uses_additional_data":false},{"leaderboard":"/sota/text-spotting-on-total-text","task":"Text Spotting","dataset":"Total-Text","model":"MaskTextSpotter v3","rank_in_archive_order":11,"of":12,"metrics":{"F-measure (%) - Full Lexicon":"78.4","F-measure (%) - No Lexicon":"71.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.09482","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}