{"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/generating-text-sequence-images-for","title":"Generating Text Sequence Images for Recognition","arxiv_id":"1901.06782","date":"2019-01-21","proceeding":null,"authors":["Yanxiang Gong","Linjie Deng","Zheng Ma","Mei Xie"],"abstract":"Recently, methods based on deep learning have dominated the field of text\nrecognition. With a large number of training data, most of them can achieve the\nstate-of-the-art performances. However, it is hard to harvest and label\nsufficient text sequence images from the real scenes. To mitigate this issue,\nseveral methods to synthesize text sequence images were proposed, yet they\nusually need complicated preceding or follow-up steps. In this work, we present\na method which is able to generate infinite training data without any auxiliary\npre/post-process. We tackle the generation task as an image-to-image\ntranslation one and utilize conditional adversarial networks to produce\nrealistic text sequence images in the light of the semantic ones. Some\nevaluation metrics are involved to assess our method and the results\ndemonstrate that the caliber of the data is satisfactory. The code and dataset\nwill be publicly available soon.","url_abs":"http://arxiv.org/abs/1901.06782v1","url_pdf":"http://arxiv.org/pdf/1901.06782v1.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":"generating-text-sequence-images-for","repo_url":"https://github.com/yxgong0/STIG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}