{"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/adversarial-generation-of-handwritten-text","title":"Adversarial Generation of Handwritten Text Images Conditioned on Sequences","arxiv_id":"1903.00277","date":"2019-03-01","proceeding":null,"authors":["Eloi Alonso","Bastien Moysset","Ronaldo Messina"],"abstract":"State-of-the-art offline handwriting text recognition systems tend to use\nneural networks and therefore require a large amount of annotated data to be\ntrained. In order to partially satisfy this requirement, we propose a system\nbased on Generative Adversarial Networks (GAN) to produce synthetic images of\nhandwritten words. We use bidirectional LSTM recurrent layers to get an\nembedding of the word to be rendered, and we feed it to the generator network.\nWe also modify the standard GAN by adding an auxiliary network for text\nrecognition. The system is then trained with a balanced combination of an\nadversarial loss and a CTC loss. Together, these extensions to GAN enable to\ncontrol the textual content of the generated word images. We obtain realistic\nimages on both French and Arabic datasets, and we show that integrating these\nsynthetic images into the existing training data of a text recognition system\ncan slightly enhance its performance.","url_abs":"http://arxiv.org/abs/1903.00277v1","url_pdf":"http://arxiv.org/pdf/1903.00277v1.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":"adversarial-generation-of-handwritten-text","repo_url":"https://github.com/fractal2k/Handwriting-Synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"ctc-loss","method_name":"CTC Loss"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.00277","atlas_url":"https://app.syntology.ai/?focus=1903.00277","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}