{"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/a-selectional-auto-encoder-approach-for","title":"A selectional auto-encoder approach for document image binarization","arxiv_id":"1706.10241","date":"2017-06-30","proceeding":null,"authors":["Jorge Calvo-Zaragoza","Antonio-Javier Gallego"],"abstract":"Binarization plays a key role in the automatic information retrieval from\ndocument images. This process is usually performed in the first stages of\ndocuments analysis systems, and serves as a basis for subsequent steps. Hence\nit has to be robust in order to allow the full analysis workflow to be\nsuccessful. Several methods for document image binarization have been proposed\nso far, most of which are based on hand-crafted image processing strategies.\nRecently, Convolutional Neural Networks have shown an amazing performance in\nmany disparate duties related to computer vision. In this paper we discuss the\nuse of convolutional auto-encoders devoted to learning an end-to-end map from\nan input image to its selectional output, in which activations indicate the\nlikelihood of pixels to be either foreground or background. Once trained,\ndocuments can therefore be binarized by parsing them through the model and\napplying a threshold. This approach has proven to outperform existing\nbinarization strategies in a number of document domains.","url_abs":"http://arxiv.org/abs/1706.10241v3","url_pdf":"http://arxiv.org/pdf/1706.10241v3.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":"a-selectional-auto-encoder-approach-for","repo_url":"https://github.com/ajgallego/document-image-binarization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"a-selectional-auto-encoder-approach-for","repo_url":"https://github.com/qurator-spk/sbb_binarization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}