{"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see the attribution page"},"url":"/paper/handwriting-recognition-of-historical","title":"Handwriting Recognition of Historical Documents with few labeled data","arxiv_id":"1811.07768","date":"2018-11-10","proceeding":null,"authors":["Chammas Edgard","Mokbel Chafic","Likforman-Sulem Laurence"],"abstract":"Historical documents present many challenges for offline handwriting\nrecognition systems, among them, the segmentation and labeling steps. Carefully\nannotated textlines are needed to train an HTR system. In some scenarios,\ntranscripts are only available at the paragraph level with no text-line\ninformation. In this work, we demonstrate how to train an HTR system with few\nlabeled data. Specifically, we train a deep convolutional recurrent neural\nnetwork (CRNN) system on only 10% of manually labeled text-line data from a\ndataset and propose an incremental training procedure that covers the rest of\nthe data. Performance is further increased by augmenting the training set with\nspecially crafted multiscale data. We also propose a model-based normalization\nscheme which considers the variability in the writing scale at the recognition\nphase. We apply this approach to the publicly available READ dataset. Our\nsystem achieved the second best result during the ICDAR2017 competition.","url_abs":"http://arxiv.org/abs/1811.07768v1","url_pdf":"http://arxiv.org/pdf/1811.07768v1.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":"handwriting-recognition-of-historical","repo_url":"https://github.com/0x454447415244/HandwritingRecognitionSystem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"htr","task_name":"HTR"},{"task_slug":"handwriting-recognition","task_name":"Handwriting Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}