{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T10:13:18Z","timestamp":1785838398679,"version":"3.56.0"},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540230601","type":"print"},{"value":"9783540286400","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-28640-0_20","type":"book-chapter","created":{"date-parts":[[2010,9,20]],"date-time":"2010-09-20T21:25:14Z","timestamp":1285017914000},"page":"213-224","source":"Crossref","is-referenced-by-count":46,"title":["Layout and Content Extraction for PDF Documents"],"prefix":"10.1007","author":[{"given":"Hui","family":"Chao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"20_CR1","unstructured":"PDF Reference, Adobe system Incorporated"},{"key":"20_CR2","unstructured":"Acrobat 4: Adobe\u2019s bid to make it more than a viewer, Walter, M. Seybold report on Internet Publishing. Vol. 3, no. 7"},{"key":"20_CR3","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/2.144436","volume":"25","author":"G. Nagy","year":"1992","unstructured":"Nagy, G., Seth, S., Viswanathan, M.: A prototype document image analysis system for technical Journals. IEEE Computer\u00a025, 10\u201322 (1992)","journal-title":"IEEE Computer"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Dengel, A.: Initial learning of document structures. In: Second International Conference on Document Analysis and Recognition (ICDAR), pp. 86\u201390 (1993)","DOI":"10.1109\/ICDAR.1993.395776"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Dengel, A., Dubiel, F.: Clustering and classification of document structure? A machine learning approach. In: ICDAR 1995, pp. 587\u2013591 (1995)","DOI":"10.1109\/ICDAR.1995.601965"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Kise, K.: Incremental acquisition of knowledge about layout structures from examples of documents. In: ICDAR 1993, pp. 668\u2013671 (1993)","DOI":"10.1109\/ICDAR.1993.395649"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Walischewski, H.: Automatic knowledge acquisition for spatial document interpretation. In: Proceedings of the Fourth ICDAR 1997, pp. 243\u2013247 (1997)","DOI":"10.1109\/ICDAR.1997.619849"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Jain, A., Yu, B.: Document representation and its application to page decomposition. IEEE Transactions on pattern analysis and machine intelligence\u00a020(3) (March 1998)","DOI":"10.1109\/34.667886"},{"key":"20_CR9","unstructured":"Smith, P.N., Brailsford, D.F.: Towards structured, block-based PDF. Electronic publishing: origination, dissemination and Design\u00a08(2-3)"},{"key":"20_CR10","unstructured":"Lovegrove, W.S., Brailsford, D.F.: Document analysis of PDF files; method, results and implications. Electronic publishing\u00a08(2-3)"},{"key":"20_CR11","unstructured":"Anjewierden, A.: AIDAS: Incremental logical structure discovery in PDF document. In: ICDAR 2001 (2001)"},{"key":"20_CR12","unstructured":"Karim, H., Rigamonti, M., Lalanne, D., Ingold, R.: Xed: a new tool for extracting hidden structure from electronic documents. In: Digital Library workshop, Palo alto (January 2004)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Haffner, P., Bottou, L., Howard, P., Cun, Y.L.: DjVu Analyzing and Compressing Scanned Documents for Internet Distribution. In: ICDAR, pp. 625\u2013628 (1999)","DOI":"10.1109\/ICDAR.1999.791865"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Fan, J.: Text extraction via an edge-bounded averaging and a parametric character model. In: Proc. Electronic Imaging 2003, Santa Clara, CA, January 22-24. SPIE, vol.\u00a05010, pp. 8\u201319 (2003)","DOI":"10.1117\/12.472839"},{"key":"20_CR15","unstructured":"Chao, H., Beretta, G., Sang, H.: PDF Document Layout Study with Page Elements and Bounding Boxes. In: DLIA 2001 (2001)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Chao, H.: Graphics Extraction in PDF Document, SPIE, vol.\u00a05010(317).","DOI":"10.1117\/12.479683"},{"key":"20_CR17","unstructured":"Chao, H.: Background extraction in multi-page PDF document. In: DLIA (2003)"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Simske, S.J., Arnabat, J.: User-directed analysis of scanned images. In: ACM workshop of Document Engineering 2003 (2003)","DOI":"10.1145\/958220.958258"},{"key":"20_CR19","unstructured":"Revankar, S.V., Fan, Z.: Image Segmentation system, U.S. Patent 5,767,978, January 21 (1997)"},{"key":"20_CR20","unstructured":"Paknad, M.D., Ayers, R.M.: Method and apparatus for identifying words described in a portable electronic document, US patent 5,832,530"},{"key":"20_CR21","unstructured":"Ayers, Robert, M.: Method and apparatus for identifying words described in a page description language file, US patent 5,832,531"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"O\u2019Rourke, Computational Geometry in C (1998)","DOI":"10.1017\/CBO9780511804120"}],"container-title":["Lecture Notes in Computer Science","Document Analysis Systems VI"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-28640-0_20.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T23:14:36Z","timestamp":1740525276000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-28640-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540230601","9783540286400"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-28640-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004]]}}}