{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T16:55:28Z","timestamp":1751475328769},"publisher-location":"Berlin, Heidelberg","reference-count":51,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642226120"},{"type":"electronic","value":"9783642226137"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-22613-7_12","type":"book-chapter","created":{"date-parts":[[2011,12,13]],"date-time":"2011-12-13T21:12:35Z","timestamp":1323810755000},"page":"221-247","source":"Crossref","is-referenced-by-count":11,"title":["Machine Learning for Document Structure Recognition"],"prefix":"10.1007","author":[{"given":"Gerhard","family":"Paa\u00df","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iuliu","family":"Konya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Akindele, O., Belaid, A.: Page segmentation by segment tracing. In: Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR), pp. 341\u2013344 (1993)","DOI":"10.1109\/ICDAR.1993.395719"},{"key":"12_CR2","first-page":"1279","volume-title":"Proc. International Conf. Document Analysis and Recognition (ICDAR)","author":"A. Antonacopoulos","year":"2007","unstructured":"Antonacopoulos, A., Gatos, B., Bridson, D.: ICDAR2007 Page Segmentation Competition. In: Proc. International Conf. Document Analysis and Recognition (ICDAR), vol.\u00a02, pp. 1279\u20131283. IEEE Computer Society, Los Alamitos (2007)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Antonacopoulos, A., Pletschacher, S., Bridson, D., Papadopoulos, C.: Icdar 2009 page segmentation competition. In: 10th International Conference on Document Analysis and Recognition, ICDAR (2009)","DOI":"10.1109\/ICDAR.2009.275"},{"key":"12_CR4","unstructured":"Awasthi, P., Gagrani, A., Ravindran, B.: Image modeling using tree structured conditional random fields. In: IJCAI (2007)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Baird, H., Casey, M.: Towards versatile document analysis systems. In: Proc. 7th International Workshop Document Analysis Systems, pp. 280\u2013290 (2006)","DOI":"10.1007\/11669487_25"},{"issue":"3","key":"12_CR6","doi-asserted-by":"publisher","first-page":"179","DOI":"10.2307\/2987782","volume":"24","author":"J. Besag","year":"1975","unstructured":"Besag, J.: Statistical analysis of non-lattice data. The Statistician\u00a024(3), 179\u2013195 (1975)","journal-title":"The Statistician"},{"key":"12_CR7","first-page":"919","volume-title":"Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR)","author":"J. Beusekom van","year":"2007","unstructured":"van Beusekom, J., Keysers, D., Shafait, F., Breuel, T.: Example-based logical labeling of document title page images. In: Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR), vol.\u00a02, pp. 919\u2013923. IEEE Computer Society, Los Alamitos (2007)"},{"key":"12_CR8","unstructured":"Breuel, T.M.: High performance document layout analysis. In: Symposium on Document Image Understanding Technology, Greenbelt, Maryland (2003)"},{"key":"12_CR9","unstructured":"Cattoni, R., Coianiz, T., Messelodi, S., Modena, C.: Geometric layout analysis techniques for document image understanding: a review. Tech. Rep. 9703-09, ITC-irst (1998), http:\/\/citeseer.comp.nus.edu.sg\/330609.html"},{"key":"12_CR10","first-page":"118","volume-title":"Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR)","author":"S. Chen","year":"2007","unstructured":"Chen, S., Mao, S., Thoma, G.: Simultaneous layout style and logical entity recognition in a heterogeneous collection of documents. In: Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 118\u2013122. IEEE Computer Society, Los Alamitos (2007)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Chidlovskii, B., Lecerf, L.: Stacked dependency networks for layout document structuring. In: SAC 2008, pp. 424\u2013428 (2008)","DOI":"10.1145\/1363686.1363790"},{"key":"12_CR12","unstructured":"DDB, Deutsche Digitale Bibliothek (2010), http:\/\/www.deutsche-digitale-bibliothek.de\/ (retrieved on December 23, 2010)"},{"key":"12_CR13","unstructured":"Dias, A.P.: Minimum spanning trees for text segmentation. In: Proc.\u00a0Annual Symposium Document Analysis and Information Retrieval (1996)"},{"key":"12_CR14","unstructured":"Doermann, D.: Page decomposition and related research. In: Proc.\u00a0Symp.\u00a0Document Image Understanding Technology, pp. 39\u201355 (1995)"},{"key":"12_CR15","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/DIAL.2004.1263262","volume-title":"Proc. 1st International Workshop Document Image Analysis for Libraries","author":"F. Esposito","year":"2004","unstructured":"Esposito, F., Malerba, D., Semeraro, G., Ferilli, S., Altamura, O., Basile, T., Berardi, M., Ceci, M., Di Mauro, N.: Machine learning methods for automatically processing historical documents: from paper acquisition to xml transformation. In: Proc. 1st International Workshop Document Image Analysis for Libraries, pp. 328\u2013335. IEEE Computer Society, Los Alamitos (2004)"},{"key":"12_CR16","unstructured":"Europeana, Europeana portal (2010), http:\/\/www.europeana.eu\/ (retrieved on December 23, 2010)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Finkel, J., Grenager, T., Manning, C.: Incorporating non-local information into information extraction systems by gibbs sampling. In: ACL (2005)","DOI":"10.3115\/1219840.1219885"},{"key":"12_CR18","first-page":"619","volume-title":"Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR)","author":"R. Furmaniak","year":"2007","unstructured":"Furmaniak, R.: Unsupervised newspaper segmentation using language context. In: Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR), vol.\u00a02, pp. 619\u2013623. IEEE Computer Society, Los Alamitos (2007)"},{"key":"12_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1007\/11551188_67","volume-title":"Pattern Recognition and Data Mining","author":"B. Gatos","year":"2005","unstructured":"Gatos, B., Danatsas, D., Pratikakis, I., Perantonis, S.J.: Automatic table detection in document images. In: Singh, S., Singh, M., Apte, C., Perner, P. (eds.) ICAPR 2005. LNCS, vol.\u00a03686, pp. 609\u2013618. Springer, Heidelberg (2005)"},{"volume-title":"Introduction to Relational Statistical Learning","year":"2007","key":"12_CR20","unstructured":"Getoor, L., Taskar, B. (eds.): Introduction to Relational Statistical Learning. MIT Press, Cambridge (2007)"},{"key":"12_CR21","unstructured":"Ha, J., Haralick, R., Phillips, I.: Document page decomposition by the bounding-box projection technique. In: Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR), pp. 1119\u20131122 (1995)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Haralick, R.: Document image understanding: Geometric and logical layout. In: Proc.\u00a0IEEE Conference on Computer Vision and Pattern Recognition, pp. 385\u2013390 (1994)","DOI":"10.1109\/CVPR.1994.323855"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Ittner, D.J., Baird, H.S.: Language-free layout analysis. In: Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR), pp. 336\u2013340 (1993)","DOI":"10.1109\/ICDAR.1993.395720"},{"issue":"3","key":"12_CR24","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1109\/34.667886","volume":"20","author":"A. Jain","year":"1998","unstructured":"Jain, A., Yu, B.: Document representation and its application to page decomposition. IEEE Trans\u00a0on Pattern Analysis and Machine Intelligence\u00a020(3), 294\u2013308 (1998)","journal-title":"IEEE Trans\u00a0on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"12_CR25","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1006\/cviu.1998.0684","volume":"70","author":"K. Kise","year":"1998","unstructured":"Kise, K., Sato, A., Iwata, M.: Segmentation of page images using the area voronoi diagram. Computer Vision and Image Understanding\u00a070(3), 370\u2013382 (1998)","journal-title":"Computer Vision and Image Understanding"},{"key":"#cr-split#-12_CR26.1","unstructured":"16. Konya, I.V., Seibert, C., Eickeler, S.: Fraunhofer newspaper segmenter - a modular document image understanding system. Journal on Document Analysis and Recognition, IJDAR (2011)"},{"key":"#cr-split#-12_CR26.2","unstructured":"17. Ijdar - expected publication in 2010 (accepted for publication)"},{"key":"12_CR27","unstructured":"Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. 18th International Conf. on ine Learning, vol.\u00a0(2001)"},{"key":"12_CR28","volume-title":"Foundations of statistical natural language processing","author":"C.D. Manning","year":"1999","unstructured":"Manning, C.D., Sch\u00fctze, H.: Foundations of statistical natural language processing. MIT Press, Cambridge (1999)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Mao, S., Rosenfeld, A., Kanungo, T.: Document structure analysis algorithms: A literature survey. In: Document Recognition and Retrieval X, SPIE, vol.\u00a05010, pp. 197\u2013207 (2003)","DOI":"10.1117\/12.476326"},{"volume-title":"Machine Learning in Document Analysis and Recognition","year":"2008","key":"12_CR30","unstructured":"Marinai, S., Fujisawa, H. (eds.): Machine Learning in Document Analysis and Recognition. Springer, Heidelberg (2008)"},{"key":"12_CR31","first-page":"653","volume":"8","author":"J. Neville","year":"2007","unstructured":"Neville, J., Jensen, D.: Relational dependency networks. Journal of Machine Learning Research\u00a08, 653\u2013692 (2007)","journal-title":"Journal of Machine Learning Research"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Niyogi, D., Srihari, S.: Knowledge-based derivation of document logical structure. In: Proc.\u00a0Int.\u00a0Conference on Document Analysis and Recognition, Montreal, Canada, pp. 472\u2013475 (1995)","DOI":"10.1109\/ICDAR.1995.599038"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Paa\u00df, G., Reichartz, F.: Exploiting semantic constraints for estimating supersenses with crfs. In: Proc. SDM 2009 (2009)","DOI":"10.1137\/1.9781611972795.42"},{"key":"12_CR34","unstructured":"Peng, F., McCallum, A.: Accurate information extraction from research papers using conditional random fields. In: HLT-NAACL 2004, pp. 329\u2013336 (2004)"},{"key":"12_CR35","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/11669487_11","volume-title":"Proc. 7th International Workshop Document Analysis Systems","author":"Y. Rangoni","year":"2006","unstructured":"Rangoni, Y., Bela\u00efd, A.: Document logical structure analysis based on perceptive cycles. In: Proc. 7th International Workshop Document Analysis Systems, pp. 117\u2013128. Springer, Heidelberg (2006)"},{"issue":"1-2","key":"12_CR36","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s10994-006-5833-1","volume":"62","author":"M. Richardson","year":"2006","unstructured":"Richardson, M., Domingos, P.: Markov logic networks. Machine Learning\u00a062(1-2), 107\u2013136 (2006)","journal-title":"Machine Learning"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Sankar, K.P., Ambati, V., Pratha, L., Jawahal, C.: Digitizing a million books: Challenges for document analysis. In: Proc. 7th International Workshop Document Analysis Systems, pp. 425\u2013436 (2006)","DOI":"10.1007\/11669487_38"},{"key":"12_CR38","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s10462-007-9019-4","volume":"25","author":"K.M. Schneider","year":"2006","unstructured":"Schneider, K.M.: Information extraction from calls for papers with conditional random fields and layout features. Artif. Intell. Rev.\u00a025, 67\u201377 (2006)","journal-title":"Artif. Intell. Rev."},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Shafait, F., Keysers, D., Breuel, T.: Performance comparison of six algorithms for page segmentation. In: 7th IAPR Workshop on Document Analysis Systems (DAS), pp. 368\u2013379 (2006)","DOI":"10.1007\/11669487_33"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Summers, K.: Near-wordless document structure classification. In: Proc.\u00a0International Conf.\u00a0on Document Analysis and Recognition (ICDAR), pp. 462\u2013465 (1995)","DOI":"10.1109\/ICDAR.1995.599036"},{"key":"12_CR41","unstructured":"Sutton, C., McCallum, A.: Collective segmentation and labeling of distant entities in information extraction. In: ICML Workshop on Statistical Relational Learning (2004)"},{"key":"12_CR42","volume-title":"Introduction to Relational Statistical Learning","author":"C. Sutton","year":"2007","unstructured":"Sutton, C., McCallum, A.: An introduction to conditional random fields for relational learning. In: Getoor, L., Taskar, B. (eds.) Introduction to Relational Statistical Learning. MIT Press, Cambridge (2007)"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Sutton, C.A., Rohanimanesh, K., McCallum, A.: Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data. In: Proc. ICML 2004 (2004)","DOI":"10.1145\/1015330.1015422"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Tang, Y., Ma, H., Mao, X., Liu, D., Suen, C.: A new approach to document analysis based on modified fractal signature. In: Proc.\u00a0International Conf.\u00a0Document Analysis and Recognition (ICDAR), pp. 567\u2013570 (1995)","DOI":"10.1109\/ICDAR.1995.601960"},{"key":"12_CR45","unstructured":"Taskar, B., Abbeel, P., Koller, D.: Discriminative probabilistic models for relational data. In: Eighteenth Conference on Uncertainty in Artificial Intelligence, UAI 2002 (2002)"},{"issue":"7","key":"12_CR46","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1109\/5.156475","volume":"80","author":"S. Tsujimoto","year":"1992","unstructured":"Tsujimoto, S., Asada, H.: Major components of a complete text reading system. Proc. IEEE\u00a080(7), 1133\u20131149 (1992)","journal-title":"Proc. IEEE"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Vincent, L.: Google book search: Document understanding on a massive scale. In: Proc. 9th International Conf. Document Analysis and Recognition, pp. 819\u2013823 (2007)","DOI":"10.1109\/ICDAR.2007.4377029"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Viola, P.A., Narasimhan, M.: Learning to extract information from semi-structured text using a discriminative context free grammar. In: SIGIR 2005, pp. 330\u2013337 (2005)","DOI":"10.1145\/1076034.1076091"},{"key":"12_CR49","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/0146-664X(82)90059-4","volume":"20","author":"F. Wahl","year":"1982","unstructured":"Wahl, F., Wong, K., Casey, R.: Block segmentation and text extraction in mixed text\/image documents. Computer Vision, Graphics, and Image Processing\u00a020, 375\u2013390 (1982)","journal-title":"Computer Vision, Graphics, and Image Processing"},{"key":"12_CR50","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-540-74976-9_30","volume-title":"Knowledge Discovery in Databases: PKDD 2007","author":"G. Wisniewski","year":"2007","unstructured":"Wisniewski, G., Gallinari, P.: Relaxation labeling for selecting and exploiting efficiently non-local dependencies in sequence labeling. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladeni\u010d, D., Skowron, A. (eds.) PKDD 2007. LNCS (LNAI), vol.\u00a04702, pp. 312\u2013323. Springer, Heidelberg (2007)"}],"container-title":["Studies in Computational Intelligence","Modeling, Learning, and Processing of Text Technological Data Structures"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-22613-7_12.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T03:08:07Z","timestamp":1606187287000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-22613-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642226120","9783642226137"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-22613-7_12","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2011]]}}}