{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T01:55:22Z","timestamp":1781661322921,"version":"3.54.5"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2019,11,30]],"date-time":"2019-11-30T00:00:00Z","timestamp":1575072000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","award":["TIN2017-85854-C4-2-R"],"award-info":[{"award-number":["TIN2017-85854-C4-2-R"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,11,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>This paper presents the \u2018NoisyOffice\u2019 database. It consists of images of printed text documents with noise mainly caused by uncleanliness from a generic office, such as coffee stains and footprints on documents or folded and wrinkled sheets with degraded printed text. This corpus is intended to train and evaluate supervised learning methods for cleaning, binarization and enhancement of noisy images of grayscale text documents. As an example, several experiments of image enhancement and binarization are presented by using deep learning techniques. Also, double-resolution images are also provided for testing super-resolution methods. The corpus is freely available at UCI Machine Learning Repository. Finally, a challenge organized by Kaggle Inc. to denoise images, using the database, is described in order to show its suitability for benchmarking of image processing systems.<\/jats:p>","DOI":"10.1093\/comjnl\/bxz098","type":"journal-article","created":{"date-parts":[[2019,8,27]],"date-time":"2019-08-27T11:32:39Z","timestamp":1566905559000},"page":"1658-1667","source":"Crossref","is-referenced-by-count":8,"title":["The NoisyOffice Database: A Corpus To Train Supervised Machine Learning Filters For Image Processing"],"prefix":"10.1093","volume":"63","author":[{"given":"M J","family":"Castro-Bleda","sequence":"first","affiliation":[{"name":"Valencian Research Institute for Artificial Intelligence, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S","family":"Espa\u00f1a-Boquera","sequence":"additional","affiliation":[{"name":"Valencian Research Institute for Artificial Intelligence, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J","family":"Pastor-Pellicer","sequence":"additional","affiliation":[{"name":"Google, Z\u00fcrich Area, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"F","family":"Zamora-Mart\u00ednez","sequence":"additional","affiliation":[{"name":"R&D Department, das-Nano S.L., Pol. Ind. Talluntxe II, Tajonar 31192, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,11,30]]},"reference":[{"key":"2020120619045312000_ref1","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1109\/34.23114","article-title":"Off-line cursive script word recognition","volume":"11","author":"Bozinovic","year":"1989","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2020120619045312000_ref2","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1109\/34.824821","article-title":"On-line and off-line handwriting recognition: a comprehensive survey","volume":"22","author":"Plamondon","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2020120619045312000_ref3","doi-asserted-by":"crossref","first-page":"1433","DOI":"10.1016\/S0031-3203(01)00129-7","article-title":"A survey on off-line cursive word recognition","volume":"35","author":"Vinciarelli","year":"2002","journal-title":"Pattern Recognit."},{"key":"2020120619045312000_ref4","first-page":"448","article-title":"Recognition of Cursive Roman Handwriting\u2014Past, Present and Future","volume-title":"Proc. 7th Int. Conf. Document Analysis and Recognition","author":"Bunke","year":"2003"},{"key":"2020120619045312000_ref5","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1016\/j.patcog.2013.05.027","article-title":"More than twenty years of advancements on frontiers in handwriting recognition","volume":"47","author":"Impedovo","year":"2014","journal-title":"Pattern Recognit."},{"key":"2020120619045312000_ref6","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/978-1-84628-726-8_12","article-title":"The State of the Art of Document Image Degradation Modelling","volume-title":"Digital Document Processing","author":"Baird","year":"2007"},{"key":"2020120619045312000_ref7","doi-asserted-by":"crossref","first-page":"2279","DOI":"10.1016\/S0031-3203(01)00178-9","article-title":"Image processing with neural networks\u2014a review","volume":"35","author":"Egmont-Petersen","year":"2002","journal-title":"Pattern Recognit."},{"key":"2020120619045312000_ref8","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/TPAMI.2005.4","article-title":"Artificial neural networks for document analysis and recognition","volume":"27","author":"Marinai","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2020120619045312000_ref9","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/s10462-012-9337-z","article-title":"Neural networks for document image preprocessing: state of the art","volume":"42","author":"Rehman","year":"2014","journal-title":"Artif. Intell. Rev."},{"key":"2020120619045312000_ref10","volume-title":"UCI machine learning repository","author":"Lichman","year":"2013"},{"key":"2020120619045312000_ref11","first-page":"1375","article-title":"ICDAR 2009 Document Image Binarization Contest (DIBCO 2009)","volume-title":"Proc. 10th Int. Conf. Document Analysis and Recognition","author":"Gatos","year":"2009"},{"key":"2020120619045312000_ref12","first-page":"1471","article-title":"ICDAR 2013 Document Image Binarization Contest (DIBCO 2013)","volume-title":"Proc. 12th Int. Conf. Document Analysis and Recognition","author":"Pratikakis","year":"2013"},{"key":"2020120619045312000_ref13","first-page":"727","article-title":"H-DIBCO 2010-Handwritten Document Image Binarization Competition","volume-title":"Proc. 12th Int. Conf. Frontiers in Handwriting Recognition","author":"Pratikakis","year":"2010"},{"key":"2020120619045312000_ref14","first-page":"809","article-title":"ICFHR 2014 Competition on Handwritten Document Image Binarization (H-DIBCO 2014)","volume-title":"Proc. 14th Int. Conf. Frontiers in Handwriting Recognition","author":"Ntirogiannis","year":"2014"},{"key":"2020120619045312000_ref15","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s10032-013-0209-0","article-title":"Efficient multiscale Sauvola\u2019s binarization","volume":"17","author":"Lazzara","year":"2014","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"2020120619045312000_ref16","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/1815330.1815331","article-title":"Ground Truth Creation for Handwriting Recognition in Historical Documents","volume-title":"Proc. 9th IAPR Int. Workshop Document Analysis Systems","author":"Fischer","year":"2010"},{"key":"2020120619045312000_ref17","first-page":"807","article-title":"An Efficient Ground Truthing Tool for Binarization of Historical Manuscripts","volume-title":"Proc. 12th Int. Conf. Document Analysis and Recognition","author":"Nafchi","year":"2013"},{"key":"2020120619045312000_ref18","first-page":"168","article-title":"AMADI_LontarSet: The First Handwritten Balinese Palm Leaf Manuscripts Dataset","volume-title":"Proc. 15th Int. Conf. Frontiers in Handwriting Recognition","author":"Kesiman","year":"2016"},{"key":"2020120619045312000_ref19","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1049\/iet-ipr.2015.0695","article-title":"Adaptive scene-text binarisation on images captured by smartphones","volume":"10","author":"Belhedi","year":"2016","journal-title":"IET Image Process."},{"key":"2020120619045312000_ref20","first-page":"663","article-title":"Document Image Ground Truth Generation from Electronic Text","volume-title":"Proc. 17th Int. Conf. Pattern Recogntion","author":"Zi","year":"2004"},{"key":"2020120619045312000_ref21","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1145\/2501115.2501127","article-title":"An Efficient Parametrization of Character Degradation Model for Semi-synthetic Image Generation","volume-title":"Proc. 2nd Int. Workshop Historical Document Imaging and Processing","author":"Kieu","year":"2013"},{"key":"2020120619045312000_ref22","first-page":"618","article-title":"Generation of Synthetic Training Data for an HMM-Based Handwriting Recognition System","volume-title":"Proc. 7th Int. Conf. Document Analysis and Recognition","author":"Varga","year":"2003"},{"key":"2020120619045312000_ref23","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1145\/2501115.2501123","article-title":"Generation of Learning Samples for Historical Handwriting Recognition Using Image Degradation","volume-title":"Proc. 2nd Int. Workshop Historical Document Imaging and Processing","author":"Fischer","year":"2013"},{"key":"2020120619045312000_ref24","doi-asserted-by":"crossref","first-page":"62","DOI":"10.3390\/jimaging3040062","article-title":"DocCreator: a new software for creating synthetic ground-Truthed document images","volume":"3","author":"Journet","year":"2017","journal-title":"J. Imaging"},{"key":"2020120619045312000_ref25","doi-asserted-by":"crossref","DOI":"10.1117\/12.912203","article-title":"A Synthetic Document Image Dataset for Developing and Evaluating Historical Document Processing Methods","volume-title":"Proc. SPIE 8297, Document Recognition and Retrieval XIX, 829710","author":"Walker","year":"2012"},{"key":"2020120619045312000_ref26","first-page":"1006","article-title":"Gradient-Domain Degradations for Improving Historical Documents Images Layout Analysis","volume-title":"Proc. 13th Int. Conf. Document Analysis and Recognition","author":"Seuret","year":"2015"},{"key":"2020120619045312000_ref27","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image super-resolution using deep convolutional networks","volume":"38","author":"Dong","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2020120619045312000_ref28","first-page":"778","article-title":"Adaptive Image Restoration of Text Images that Contain Touching or Broken Characters","volume-title":"Proc. 3rd Int. Conf. Document Analysis and Recognition","author":"Stubberud","year":"1995"},{"key":"2020120619045312000_ref29","first-page":"275","article-title":"A Two-Stage Binarization Approach for Document Images","volume-title":"Proc. Int. Symposium Intelligent Multimedia, Video and Speech Processing","author":"Chi","year":"2001"},{"key":"2020120619045312000_ref30","doi-asserted-by":"crossref","first-page":"1582","DOI":"10.1109\/TPAMI.2003.1251151","article-title":"Neural edge enhancer for supervised edge enhancement from Noisy images","volume":"25","author":"Suzuki","year":"2003","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2020120619045312000_ref31","doi-asserted-by":"crossref","DOI":"10.1007\/11492429_46","article-title":"Enhancement and cleaning of handwritten data by using neural networks","volume-title":"Pattern Recognition and Image Analysis. IbPRIA 2005","author":"Hidalgo","year":"2005"},{"key":"2020120619045312000_ref32","first-page":"517","article-title":"Contextual Restoration of Severely Degraded Document Images","volume-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","author":"Banerjee","year":"2009"},{"key":"2020120619045312000_ref33","first-page":"47","article-title":"A survey on image enhancement techniques","volume":"4","author":"Gupta","year":"2015","journal-title":"Int. J. Electrical Electron. Eng. Telecommunications"},{"key":"2020120619045312000_ref34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-19222-2_10","article-title":"Insights on the Use of Convolutional Neural Networks for Document Image Binarization","volume-title":"Advances in Computational Intelligence. IWANN 2015","author":"Pastor-Pellicer","year":"2015"},{"key":"2020120619045312000_ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-73053-8_33","article-title":"Efficient BP Algorithms for General Feedforward Neural Networks","volume-title":"Bio-inspired Modeling of Cognitive Tasks. IWINAC 2007. Lecture Notes in Computer Science","author":"Espa\u00f1a-Boquera","year":"2007"},{"key":"2020120619045312000_ref36","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-73007-1_18","article-title":"Behaviour-based Clustering of Neural Networks Applied to Document Enhancement","volume-title":"Computational and Ambient Intelligence. IWANN 2007. Lecture Notes in Computer Science","author":"Zamora-Mart\u00ednez","year":"2007"},{"key":"2020120619045312000_ref37","article-title":"Convolutional Networks for Images, Speech, and Time Series","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"LeCun","year":"1995"},{"key":"2020120619045312000_ref38","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-74690-4_56","article-title":"Multi-dimensional Recurrent Neural Networks","volume-title":"Artificial Neural Networks. ICANN 2007. Lecture Notes in Computer Science","author":"Graves","year":"2007"},{"key":"2020120619045312000_ref39","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"2020120619045312000_ref40","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"key":"2020120619045312000_ref41","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/S0031-3203(99)00055-2","article-title":"Adaptive document image binarization","volume":"33","author":"Sauvola","year":"2000","journal-title":"Pattern Recognit."},{"key":"2020120619045312000_ref42","first-page":"1037","article-title":"Text Localization, Enhancement and Binarization in Multimedia Documents","volume-title":"Proc. 16th Int. Conf. Pattern Recognition","author":"Wolf","year":"2002"},{"key":"2020120619045312000_ref43","first-page":"160","article-title":"Minimum Error Rate Training in Statistical Machine Translation","volume-title":"Proc. 41st Annual Meeting Association for Computational Linguistics","author":"Och","year":"2003"},{"key":"2020120619045312000_ref44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-19222-2_50","article-title":"esCam: A Mobile Application to Capture and Enhance Text Images","volume-title":"Advances in Computational Intelligence. IWANN 2015. Lecture Notes in Computer Science","author":"Pastor-Pellicer","year":"2015"},{"key":"2020120619045312000_ref45","volume-title":"Google drive","author":"Inc","year":"2016"},{"key":"2020120619045312000_ref46","volume-title":"Camscanner-phone pdf creator","author":"INTSIG Information Co., Ltd","year":"2016"},{"key":"2020120619045312000_ref47","volume-title":"Evernote scannable","author":"Evernote","year":"2016"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/comjnl\/article-pdf\/63\/11\/1658\/34314962\/bxz098.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/comjnl\/article-pdf\/63\/11\/1658\/34314962\/bxz098.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,7]],"date-time":"2020-12-07T00:12:39Z","timestamp":1607299959000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/63\/11\/1658\/5648014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,30]]},"references-count":47,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2019,11,30]]},"published-print":{"date-parts":[[2020,11,19]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxz098","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,11]]},"published":{"date-parts":[[2019,11,30]]}}}