{"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/improving-document-binarization-via","title":"Improving Document Binarization via Adversarial Noise-Texture Augmentation","arxiv_id":"1810.11120","date":"2018-10-25","proceeding":null,"authors":["Ankan Kumar Bhunia","Ayan Kumar Bhunia","Aneeshan Sain","Partha Pratim Roy"],"abstract":"Binarization of degraded document images is an elementary step in most of the\nproblems in document image analysis domain. The paper re-visits the\nbinarization problem by introducing an adversarial learning approach. We\nconstruct a Texture Augmentation Network that transfers the texture element of\na degraded reference document image to a clean binary image. In this way, the\nnetwork creates multiple versions of the same textual content with various\nnoisy textures, thus enlarging the available document binarization datasets. At\nlast, the newly generated images are passed through a Binarization network to\nget back the clean version. By jointly training the two networks we can\nincrease the adversarial robustness of our system. Also, it is noteworthy that\nour model can learn from unpaired data. Experimental results suggest that the\nproposed method achieves superior performance over widely used DIBCO datasets.","url_abs":"http://arxiv.org/abs/1810.11120v2","url_pdf":"http://arxiv.org/pdf/1810.11120v2.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":"improving-document-binarization-via","repo_url":"https://github.com/ankanbhunia/AdverseBiNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}