{"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/deeptext-a-unified-framework-for-text","title":"DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images","arxiv_id":"1605.07314","date":"2016-05-24","proceeding":null,"authors":["Zhuoyao Zhong","Lianwen Jin","Shuye Zhang","Ziyong Feng"],"abstract":"In this paper, we develop a novel unified framework called DeepText for text\nregion proposal generation and text detection in natural images via a fully\nconvolutional neural network (CNN). First, we propose the inception region\nproposal network (Inception-RPN) and design a set of text characteristic prior\nbounding boxes to achieve high word recall with only hundred level candidate\nproposals. Next, we present a powerful textdetection network that embeds\nambiguous text category (ATC) information and multilevel region-of-interest\npooling (MLRP) for text and non-text classification and accurate localization.\nFinally, we apply an iterative bounding box voting scheme to pursue high recall\nin a complementary manner and introduce a filtering algorithm to retain the\nmost suitable bounding box, while removing redundant inner and outer boxes for\neach text instance. Our approach achieves an F-measure of 0.83 and 0.85 on the\nICDAR 2011 and 2013 robust text detection benchmarks, outperforming previous\nstate-of-the-art results.","url_abs":"http://arxiv.org/abs/1605.07314v1","url_pdf":"http://arxiv.org/pdf/1605.07314v1.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":"deeptext-a-unified-framework-for-text","repo_url":"https://github.com/kingcong/gpu_deeptext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":null},{"paper_slug":"deeptext-a-unified-framework-for-text","repo_url":"https://github.com/yangyucheng000/ascend_deeptext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":null},{"paper_slug":"deeptext-a-unified-framework-for-text","repo_url":"https://github.com/2023-MindSpore-1/ms-code-171","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"deeptext-a-unified-framework-for-text","repo_url":"https://github.com/2023-MindSpore-4/Code1/tree/main/DeepText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"deeptext-a-unified-framework-for-text","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/cv/deeptext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}