{"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/fused-text-segmentation-networks-for-multi","title":"Fused Text Segmentation Networks for Multi-oriented Scene Text Detection","arxiv_id":"1709.03272","date":"2017-09-11","proceeding":null,"authors":["Yuchen Dai","Zheng Huang","Yuting Gao","Youxuan Xu","Kai Chen","Jie Guo","Weidong Qiu"],"abstract":"In this paper, we introduce a novel end-end framework for multi-oriented\nscene text detection from an instance-aware semantic segmentation perspective.\nWe present Fused Text Segmentation Networks, which combine multi-level features\nduring the feature extracting as text instance may rely on finer feature\nexpression compared to general objects. It detects and segments the text\ninstance jointly and simultaneously, leveraging merits from both semantic\nsegmentation task and region proposal based object detection task. Not\ninvolving any extra pipelines, our approach surpasses the current state of the\nart on multi-oriented scene text detection benchmarks: ICDAR2015 Incidental\nScene Text and MSRA-TD500 reaching Hmean 84.1% and 82.0% respectively. Morever,\nwe report a baseline on total-text containing curved text which suggests\neffectiveness of the proposed approach.","url_abs":"http://arxiv.org/abs/1709.03272v4","url_pdf":"http://arxiv.org/pdf/1709.03272v4.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":[],"tasks":[{"task_slug":"multi-oriented-scene-text-detection","task_name":"Multi-Oriented Scene Text Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"text-detection","task_name":"Text Detection"},{"task_slug":"text-segmentation","task_name":"Text Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"FTSN + MNMS","rank_in_archive_order":28,"of":43,"metrics":{"F-Measure":"84.1","Precision":"88.6","Recall":"80"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-msra-td500","task":"Scene Text Detection","dataset":"MSRA-TD500","model":"FTSN + MNMS","rank_in_archive_order":12,"of":18,"metrics":{"F-Measure":"82","Precision":"87.6","Recall":"77.1"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset":"Total-Text","model":"FTSN","rank_in_archive_order":21,"of":27,"metrics":{"F-Measure":"81.3%","Precision":"84.7","Recall":"78"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.03272","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}