{"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/scene-text-detection-with-supervised-pyramid","title":"Scene Text Detection with Supervised Pyramid Context Network","arxiv_id":"1811.08605","date":"2018-11-21","proceeding":null,"authors":["Enze Xie","Yuhang Zang","Shuai Shao","Gang Yu","Cong Yao","Guangyao Li"],"abstract":"Scene text detection methods based on deep learning have achieved remarkable\nresults over the past years. However, due to the high diversity and complexity\nof natural scenes, previous state-of-the-art text detection methods may still\nproduce a considerable amount of false positives, when applied to images\ncaptured in real-world environments. To tackle this issue, mainly inspired by\nMask R-CNN, we propose in this paper an effective model for scene text\ndetection, which is based on Feature Pyramid Network (FPN) and instance\nsegmentation. We propose a supervised pyramid context network (SPCNET) to\nprecisely locate text regions while suppressing false positives. Benefited from\nthe guidance of semantic information and sharing FPN, SPCNET obtains\nsignificantly enhanced performance while introducing marginal extra\ncomputation. Experiments on standard datasets demonstrate that our SPCNET\nclearly outperforms start-of-the-art methods. Specifically, it achieves an\nF-measure of 92.1% on ICDAR2013, 87.2% on ICDAR2015, 74.1% on ICDAR2017 MLT and\n82.9% on Total-Text.","url_abs":"http://arxiv.org/abs/1811.08605v1","url_pdf":"http://arxiv.org/pdf/1811.08605v1.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":"scene-text-detection-with-supervised-pyramid","repo_url":"https://github.com/AirBernard/Scene-Text-Detection-with-SPCNET","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"scene-text-detection-with-supervised-pyramid","repo_url":"https://github.com/brooklyn1900/SPCNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpn","method_name":"FPN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset":"ICDAR 2013","model":"SPCNET","rank_in_archive_order":2,"of":16,"metrics":{"F-Measure":"92.1%","Precision":"93.8","Recall":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"SPCNET","rank_in_archive_order":15,"of":43,"metrics":{"F-Measure":"87.2","Precision":"88.7","Recall":"85.8"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2017-mlt-1","task":"Scene Text Detection","dataset":"ICDAR 2017 MLT","model":"SPCNET","rank_in_archive_order":7,"of":14,"metrics":{"F-Measure":"74.1%","Precision":"80.6","Recall":"68.6"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset":"Total-Text","model":"SPCNET","rank_in_archive_order":19,"of":27,"metrics":{"F-Measure":"82.9%","Precision":"83","Recall":"82.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.08605","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}