{"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/word-recognition-with-deep-conditional-random","title":"Word Recognition with Deep Conditional Random Fields","arxiv_id":"1612.01072","date":"2016-12-04","proceeding":null,"authors":["Gang Chen","Yawei Li","Sargur N. Srihari"],"abstract":"Recognition of handwritten words continues to be an important problem in\ndocument analysis and recognition. Existing approaches extract hand-engineered\nfeatures from word images--which can perform poorly with new data sets.\nRecently, deep learning has attracted great attention because of the ability to\nlearn features from raw data. Moreover they have yielded state-of-the-art\nresults in classification tasks including character recognition and scene\nrecognition. On the other hand, word recognition is a sequential problem where\nwe need to model the correlation between characters. In this paper, we propose\nusing deep Conditional Random Fields (deep CRFs) for word recognition.\nBasically, we combine CRFs with deep learning, in which deep features are\nlearned and sequences are labeled in a unified framework. We pre-train the deep\nstructure with stacked restricted Boltzmann machines (RBMs) for feature\nlearning and optimize the entire network with an online learning algorithm. The\nproposed model was evaluated on two datasets, and seen to perform significantly\nbetter than competitive baseline models. The source code is available at\nhttps://github.com/ganggit/deepCRFs.","url_abs":"http://arxiv.org/abs/1612.01072v1","url_pdf":"http://arxiv.org/pdf/1612.01072v1.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":"word-recognition-with-deep-conditional-random","repo_url":"https://github.com/ganggit/deepCRFs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"scene-recognition","task_name":"Scene Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}