{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T06:00:11Z","timestamp":1783231211107,"version":"3.54.6"},"reference-count":156,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"KS2 Company"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3360528","type":"journal-article","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T18:37:31Z","timestamp":1706726251000},"page":"19872-19886","source":"Crossref","is-referenced-by-count":18,"title":["An Overview of Data Extraction From Invoices"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2894-9915","authenticated-orcid":false,"given":"Thomas","family":"Saout","sequence":"first","affiliation":[{"name":"LERIA, SFR MATHSTIC, University of Angers, Angers, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8636-3870","authenticated-orcid":false,"given":"Fr\u00e9d\u00e9ric","family":"Lardeux","sequence":"additional","affiliation":[{"name":"LERIA, SFR MATHSTIC, University of Angers, Angers, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fr\u00e9d\u00e9ric","family":"Saubion","sequence":"additional","affiliation":[{"name":"LERIA, SFR MATHSTIC, University of Angers, Angers, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icdar.1993.395796"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0074-5_6"},{"key":"ref3","article-title":"An unsupervised method for general named entity recognition and automated concept discovery","volume-title":"Proc. 1st Int. Conf. Gen. WordNet","author":"Alfonseca"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/fi10120123"},{"key":"ref5","article-title":"Automatic invoice data extraction as a constraint satisfaction problem","author":"Andersson","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3192828"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001494000516"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109419"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/make2040033"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s41870-023-01610-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/data6070078"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3072900"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22913-8_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0066174"},{"key":"ref15","volume-title":"Graphs and Hypergraphs","author":"Berge","year":"1985"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-018-0296-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1165485.1165506"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1117\/12.783598"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297461"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3167418"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1997.619865"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DEXA.1997.617381"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2002.1047838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973068.97"},{"key":"ref25","article-title":"Complicated table structure recognition","author":"Chi","year":"2019","journal-title":"arXiv:1908.04729"},{"key":"ref26","first-page":"827","article-title":"Rule-based information extraction is dead! long live rule-based information extraction systems!","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Chiticariu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27443-5_14"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/800157.805047"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3085228.3085278"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2018.29"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45869-7_47"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref35","first-page":"1","article-title":"The automatic content extraction (ACE) program\u2014Tasks, data, and evaluation","volume-title":"Proc. 4th Int. Conf. Lang. Resour. Eval.","author":"Doddington"},{"key":"ref36","article-title":"Fine-grained named entity recognition using ELMo and Wikidata","author":"Dogan","year":"2019","journal-title":"arXiv:1904.10503"},{"key":"ref37","volume-title":"Optical Character Recognition","author":"Eikvil","year":"1993"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-006-0017-x"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1117\/12.908542"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1075\/cilt.260.29eva"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.304"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-12837-0_6","volume-title":"Semantic Processing of Legal Texts: Where the Language of Law Meets the Law of Language","volume":"6036","author":"Francesconi","year":"2010"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/info10080248"},{"key":"ref44","article-title":"Complete scanning application using OpenCv","author":"Gangal","year":"2021","journal-title":"arXiv:2107.03700"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956590"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.131"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2960811.2967173"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2505377"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116601"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3295776"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86331-9_45"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IALP48816.2019.9037668"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/math11041054"},{"key":"ref56","article-title":"The workflow reference model","author":"Hollingsworth","year":"1994"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref59","article-title":"A survey on optical character recognition system","author":"Islam","year":"2017","journal-title":"J. Inf. Commun. Technol."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4761550"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2876035"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.2307\/249710"},{"key":"ref64","article-title":"Deep learning for table detection and structure recognition: A survey","author":"Kasem","year":"2022","journal-title":"arXiv:2211.08469"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108942"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09720-9"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30645-8_27"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00220"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48172-9_21"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1142\/9789812797704_0012"},{"issue":"3","key":"ref72","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1080\/09747338.1976.11450168","article-title":"Character recognition","volume":"17","author":"Srihari","year":"1976","journal-title":"IETE J. Educ."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11819-7"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981314"},{"key":"ref76","first-page":"1918","article-title":"TableBank: Table benchmark for image-based table detection and recognition","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Li"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68790-8_50"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/1255175.1255193"},{"key":"ref81","article-title":"Advanced document analysis and automatic classification of PDF documents","author":"Lovegrove","year":"1996"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.5220\/0011682600003411"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(86)90040-3"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3569095"},{"key":"ref85","article-title":"MUC-7 evaluation of IE technology: Overview of results","volume-title":"Proc. Conf. 7th Message Understand.","author":"Marsh"},{"key":"ref86","first-page":"542","article-title":"Everything you always wanted to know about the parameterized complexity of subgraph isomorphism (but were afraid to ask)","volume-title":"Proc. 31st Int. Symp. Theor. Aspects Comput. Sci.","author":"Marx"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51372-6_19"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-010-0137-1"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3012542"},{"key":"ref90","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. 1st Int. Conf. Learn. Represent.","author":"Mikolov"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"issue":"1","key":"ref92","first-page":"72","article-title":"Optical character recognition","volume":"2","author":"Mithe","year":"2013","journal-title":"Int. J. Recent Technol. Eng."},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/5.156468"},{"key":"ref94","article-title":"Geometric constraint solver","author":"Moussaoui","year":"2016"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1075\/li.30.1.03nad"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3110787"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ARES.2010.50"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3476887.3476888"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10484"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"ref101","article-title":"CORD: A consolidated receipt dataset for post-OCR parsing","volume-title":"Proc. Workshop Document Intell. (NeurIPS)","author":"Park"},{"key":"ref102","article-title":"Abstractive information extraction from scanned invoices (AIESI) using end-to-end sequential approach","author":"Patel","year":"2020","journal-title":"arXiv:2009.05728"},{"key":"ref103","article-title":"TAO: System for table detection and extraction from PDF documents","volume-title":"Proc. 29th Int. Flairs Conf.","author":"Perez-Arriaga"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860479"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2973502"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_7"},{"key":"ref110","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_5"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92013-9_30"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00028"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357694"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.271"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38628-2_91"},{"key":"ref117","article-title":"A two-stage approach for table extraction in invoices","author":"Saout","year":"2022","journal-title":"arXiv:2210.04716"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.192"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.181"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/1815330.1815339"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1108\/EEMCS-03-2017-0035"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99972-2_20"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00226"},{"key":"ref125","first-page":"239","article-title":"Adapting word2vec to named entity recognition","volume-title":"Proc. 20th Nordic Conf. Comput. Linguistics","author":"Sien\u010dnik"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20081-7_1"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/1860559.1860599"},{"key":"ref129","article-title":"Establishing a new state-of-the-art for French named entity recognition","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Su\u00e1rez"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2901943"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/JEEIT.2019.8717504"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/BF02626999"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00027"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-39940-9_158"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851886"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57058-3_19"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOMP.2019.8679233"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2001.953845"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995049"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3201203"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1002\/int.22957"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00133"},{"key":"ref144","first-page":"2145","article-title":"A survey on recent advances in named entity recognition from deep learning models","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Yadav"},{"key":"ref145","first-page":"1013","article-title":"Collective cross-document relation extraction without labelled data","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Yao"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3191784"},{"key":"ref148","first-page":"1773","article-title":"pdf2table: A method to extract table information from PDF files","volume-title":"Proc. IICAI","author":"Yildiz"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-004-0120-9"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2017.8393390"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413069"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_8"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3123154"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10418145.pdf?arnumber=10418145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:28:28Z","timestamp":1707812908000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":156,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3360528","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}