{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T20:56:43Z","timestamp":1780779403459,"version":"3.54.1"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540321408","type":"print"},{"value":"9783540321576","type":"electronic"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11669487_12","type":"book-chapter","created":{"date-parts":[[2006,1,19]],"date-time":"2006-01-19T08:46:59Z","timestamp":1137660419000},"page":"129-140","source":"Crossref","is-referenced-by-count":37,"title":["A System for Converting PDF Documents into Structured XML Format"],"prefix":"10.1007","author":[{"given":"Herv\u00e9","family":"D\u00e9jean","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Luc","family":"Meunier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"12_CR1","unstructured":"Wikipedia, \n                    \n                      http:\/\/www.wikipedia.org"},{"key":"12_CR2","unstructured":"PDF Reference, 5th edn., Adobe\u00ae Portable Document Format"},{"key":"12_CR3","unstructured":"CambridgeDoc, \n                    \n                      http:\/\/www.cambridgedoc.com"},{"key":"12_CR4","unstructured":"JPedal, \n                    \n                      http:\/\/www.jpedal.org"},{"key":"12_CR5","unstructured":"PDFTron, \n                    \n                      http:\/\/www.pdftron.com"},{"key":"12_CR6","unstructured":"Hadjar, K., Rigamonti, M., Lalanne, D., Ingold, R.: Xed: a new Tool for eXtracting hidden structures from electronic Documents. In: DIAL (2004)"},{"key":"12_CR7","unstructured":"Omnipp. 14, Scansoft, \n                    \n                      http:\/\/www.scansoft.com"},{"key":"12_CR8","unstructured":"ABBYY FineReader, \n                    \n                      http:\/\/www.abbyy.com\/"},{"key":"12_CR9","unstructured":"Adobe Acrobat Capture"},{"key":"12_CR10","unstructured":"Xpdf, \n                    \n                      http:\/\/www.foolabs.com\/xpdf\/"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Kuich, W., Salomaa, A.: Semirings, Automata, Languages. In: EATCS Monographs, on Theoretical Computer Science. Springer, Heidelberg (1986)","DOI":"10.1007\/978-3-642-69959-7"},{"key":"12_CR12","unstructured":"Lin, X.: Header and Footer Extraction by Page-Association, Hewlett-Packard Technical Report (2002), \n                    \n                      http:\/\/www.hpl.hp.com\/techreports\/2002\/HPL-2002-129.pdf"},{"key":"12_CR13","unstructured":"Cattoni, R., Coianiz, T., Messelodi, S., Modena, C.M.: Geometric Layout Analysis Techniques for Document Image Understanding: a Review, ITC-IRST Technical Report #9703-09"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Meunier, J.-L.: Optimized XY-Cut for Determining a Page Reading Order. In: ICDAR 2005 (2005)","DOI":"10.1109\/ICDAR.2005.182"},{"key":"12_CR15","unstructured":"Nagy, G., Seth, S.: Hierarchical representation of optically scanned documents. In: International Conference on Pattern Recognition (1984)"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Aiello, M., Smeulders, A.: Thick 2D Relations for Document Understanding. In: 7th Joint Conference on Information Sciences (2003)","DOI":"10.1016\/j.ins.2003.05.015"},{"key":"12_CR17","unstructured":"Breuel, T.M.: High performance document layout analysis. In: Symposium on Document Image Understanding (2003)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"D\u00e9jean, H., Meunier, J.-L.: Structuring documents according to their ToC, DocEng (2005)","DOI":"10.1145\/1096601.1096605"},{"key":"12_CR19","unstructured":"Dori, D., Doermann, D., Shin, C., Haralick, R., Buchman, M., Ross, D., Phillips, I.: The representation of Document Structure. In: Hansbooks on optical Character Recognition and Document Analysis. World Scientific Publishing Company, Singapore (1996)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis Systems VII"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11669487_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T14:21:23Z","timestamp":1558275683000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11669487_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540321408","9783540321576"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/11669487_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006]]}}}