{"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/efficient-scene-text-localization-and","title":"Efficient Scene Text Localization and Recognition with Local Character Refinement","arxiv_id":"1504.03522","date":"2015-04-14","proceeding":null,"authors":["Lukáš Neumann","Jiří Matas"],"abstract":"An unconstrained end-to-end text localization and recognition method is\npresented. The method detects initial text hypothesis in a single pass by an\nefficient region-based method and subsequently refines the text hypothesis\nusing a more robust local text model, which deviates from the common assumption\nof region-based methods that all characters are detected as connected\ncomponents.\n  Additionally, a novel feature based on character stroke area estimation is\nintroduced. The feature is efficiently computed from a region distance map, it\nis invariant to scaling and rotations and allows to efficiently detect text\nregions regardless of what portion of text they capture.\n  The method runs in real time and achieves state-of-the-art text localization\nand recognition results on the ICDAR 2013 Robust Reading dataset.","url_abs":"http://arxiv.org/abs/1504.03522v1","url_pdf":"http://arxiv.org/pdf/1504.03522v1.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":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset":"ICDAR 2013","model":"Neumann et al. *","rank_in_archive_order":14,"of":16,"metrics":{"F-Measure":"77.1%","Precision":"81.8","Recall":"72.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}