{"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/accurate-text-localization-in-natural-image","title":"Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network","arxiv_id":"1603.09423","date":"2016-03-31","proceeding":null,"authors":["Tong He","Weilin Huang","Yu Qiao","Jian Yao"],"abstract":"We introduce a new top-down pipeline for scene text detection. We propose a\nnovel Cascaded Convolutional Text Network (CCTN) that joints two customized\nconvolutional networks for coarse-to-fine text localization. The CCTN fast\ndetects text regions roughly from a low-resolution image, and then accurately\nlocalizes text lines from each enlarged region. We cast previous character\nbased detection into direct text region estimation, avoiding multiple bottom-\nup post-processing steps. It exhibits surprising robustness and discriminative\npower by considering whole text region as detection object which provides\nstrong semantic information. We customize convolutional network by develop- ing\nrectangle convolutions and multiple in-network fusions. This enables it to\nhandle multi-shape and multi-scale text efficiently. Furthermore, the CCTN is\ncomputationally efficient by sharing convolutional computations, and high-level\nproperty allows it to be invariant to various languages and multiple\norientations. It achieves 0.84 and 0.86 F-measures on the ICDAR 2011 and ICDAR\n2013, delivering substantial improvements over state-of-the-art results [23,\n1].","url_abs":"http://arxiv.org/abs/1603.09423v1","url_pdf":"http://arxiv.org/pdf/1603.09423v1.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":"accurate-text-localization-in-natural-image","repo_url":"https://github.com/apekshapriya/Text-Localization-in-Image","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}