{"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-handwritten-chinese-characters","title":"Generating Handwritten Chinese Characters using CycleGAN","arxiv_id":"1801.08624","date":"2018-01-25","proceeding":null,"authors":["Bo Chang","Qiong Zhang","Shenyi Pan","Lili Meng"],"abstract":"Handwriting of Chinese has long been an important skill in East Asia.\nHowever, automatic generation of handwritten Chinese characters poses a great\nchallenge due to the large number of characters. Various machine learning\ntechniques have been used to recognize Chinese characters, but few works have\nstudied the handwritten Chinese character generation problem, especially with\nunpaired training data. In this work, we formulate the Chinese handwritten\ncharacter generation as a problem that learns a mapping from an existing\nprinted font to a personalized handwritten style. We further propose DenseNet\nCycleGAN to generate Chinese handwritten characters. Our method is applied not\nonly to commonly used Chinese characters but also to calligraphy work with\naesthetic values. Furthermore, we propose content accuracy and style\ndiscrepancy as the evaluation metrics to assess the quality of the handwritten\ncharacters generated. We then use our proposed metrics to evaluate the\ngenerated characters from CASIA dataset as well as our newly introduced Lanting\ncalligraphy dataset.","url_abs":"http://arxiv.org/abs/1801.08624v1","url_pdf":"http://arxiv.org/pdf/1801.08624v1.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-handwritten-chinese-characters","repo_url":"https://github.com/changebo/HCCG-CycleGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"generating-handwritten-chinese-characters","repo_url":"https://github.com/SamuelNguyen1998/Vietnamese_Handwriting_Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generating-handwritten-chinese-characters","repo_url":"https://github.com/huyhoang17/Vietnamese_Handwriting_Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1801.08624","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}