{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T14:44:09Z","timestamp":1775054649607,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T00:00:00Z","timestamp":1404172800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1007\/s10032-014-0225-8","type":"journal-article","created":{"date-parts":[[2014,6,30]],"date-time":"2014-06-30T02:29:42Z","timestamp":1404095382000},"page":"331-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Multimodal page classification in administrative document image streams"],"prefix":"10.1007","volume":"17","author":[{"given":"Mar\u00e7al","family":"Rusi\u00f1ol","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volkmar","family":"Frinken","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew D.","family":"Bagdanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josep","family":"Llad\u00f3s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,7,1]]},"reference":[{"key":"225_CR1","volume-title":"Mining Text Data, Chap. A Survey of Text Classification Algorithms","author":"C Aggarwal","year":"2012","unstructured":"Aggarwal, C., Zhai, C.: Mining Text Data, Chap. A Survey of Text Classification Algorithms. Springer, New York (2012)"},{"key":"225_CR2","doi-asserted-by":"crossref","unstructured":"Augereau, O., Journet, N., Vialard, A., Domenger, J.: Improving classification of an industrial document image database by combining visual and textual features. In: Proceedings of the Eleventh IAPR International Workshop on Document Analysis Systems (2014)","DOI":"10.1109\/DAS.2014.44"},{"key":"225_CR3","doi-asserted-by":"crossref","unstructured":"Bagdanov, A.: Fine-grained document genre classification using first order random graphs. In: Proceedings of the Sixth International Conference on Document Analysis and Recognition, pp. 79\u201383 (2001)","DOI":"10.1109\/ICDAR.2001.953759"},{"key":"225_CR4","doi-asserted-by":"crossref","unstructured":"van Beusekom, J., Keysers, D., Shafait, F., Breuel, T.: Distance measures for layout-based document image retrieval. In: Proceedings of the International Conference on Document Image Analysis for Libraries (2006)","DOI":"10.1109\/DIAL.2006.16"},{"key":"225_CR5","unstructured":"Blei, D., Ng, A., Jordan, M.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)"},{"key":"225_CR6","doi-asserted-by":"crossref","unstructured":"Cesarini, F., Lastri, M., Marinai, S., Soda, G.: Encoding of modified X-Y trees for document classification. In: Proceedings of the Sixth International Conference on Document Analysis and Recognition, pp. 1131\u20131136 (2001)","DOI":"10.1109\/ICDAR.2001.953962"},{"issue":"3","key":"225_CR7","doi-asserted-by":"crossref","first-page":"27:1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C Chang","year":"2011","unstructured":"Chang, C., Lin, C.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27:1\u201327:27 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"1","key":"225_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10032-006-0020-2","volume":"10","author":"N Chen","year":"2006","unstructured":"Chen, N., Blostein, D.: A survey of document image classification: problem statement, classifier architecture and performance evaluation. Int. J. Document Anal. Recognit. 10(1), 1\u201316 (2006)","journal-title":"Int. J. Document Anal. Recognit."},{"issue":"6","key":"225_CR9","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"S Deerwester","year":"1990","unstructured":"Deerwester, S., Dumais, S., Furnas, G., Landauer, T., Harshman, R.: Indexing by latent semantic analysis. J. Am. Soc. Inf. Sci. 41(6), 391\u2013407 (1990)","journal-title":"J. Am. Soc. Inf. Sci."},{"issue":"4","key":"225_CR10","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1002\/(SICI)1098-1098(199624)7:4<271::AID-IMA2>3.0.CO;2-5","volume":"7","author":"A Dengel","year":"1996","unstructured":"Dengel, A., Dubiel, F.: Computer understanding of document structure. Int. J. Imaging Syst. Technol. 7(4), 271\u2013278 (1996)","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"225_CR11","unstructured":"Dimmick, D., Garris, M., Wilson, C.L.: Structured forms database. Tech. rep, National Institutte of Standards and Technology (1991)"},{"issue":"3","key":"225_CR12","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1006\/cviu.1998.0692","volume":"70","author":"D Doermann","year":"1998","unstructured":"Doermann, D.: The indexing and retrieval of document images: a survey. Comput. Vis. Image Underst. 70(3), 287\u2013298 (1998)","journal-title":"Comput. Vis. Image Underst."},{"key":"225_CR13","volume-title":"Pattern Classification","author":"R Duda","year":"2000","unstructured":"Duda, R., Hart, P., Stork, D.: Pattern Classification. Wiley-Interscience, New York (2000)"},{"key":"225_CR14","doi-asserted-by":"crossref","unstructured":"Erol, B., Hull, J.: Semantic classification of business images. In: Electronic Imaging, pp. 60,730G\u201360,730G (2006)","DOI":"10.1117\/12.643463"},{"key":"225_CR15","unstructured":"Ford, G., Thoma, G.: Ground truth data for document image analysis. In: Proceedings of the Symposium on Document Image Understanding and Technology, pp. 199\u2013205 (2003)"},{"key":"225_CR16","doi-asserted-by":"crossref","unstructured":"Gaceb, D., Eglin, V., Lebourgeois, F.: Classification of business documents for real-time application. J. Real-time Image Process. (2011). doi: 10.1007\/s11554-011-0227-4","DOI":"10.1007\/s11554-011-0227-4"},{"key":"225_CR17","doi-asserted-by":"crossref","unstructured":"Gordo, A., Gibert, J., Valveny, E., Rusi\u00f1ol, M.: A kernel-based approach to document retrieval. In: Proceedings of the Ninth IAPR International Workshop on Document Analysis Systems, pp. 377\u2013384 (2010)","DOI":"10.1145\/1815330.1815379"},{"key":"225_CR18","doi-asserted-by":"crossref","unstructured":"Gordo, A., Perronnin, F.: A bag-of-pages approach to unordered multi-page document classification. In: International Conference on Pattern Recognition, pp. 1920\u20131923 (2010)","DOI":"10.1109\/ICPR.2010.473"},{"key":"225_CR19","doi-asserted-by":"crossref","unstructured":"Gordo, A., Perronnin, F., Valveny, E.: Document classification using multiple views. In: Proceedings of the Tenth IAPR International Workshop on Document Analysis Systems, pp. 33\u201337 (2012)","DOI":"10.1109\/DAS.2012.30"},{"issue":"7","key":"225_CR20","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1016\/j.patcog.2012.12.004","volume":"46","author":"A Gordo","year":"2013","unstructured":"Gordo, A., Perronnin, F., Valveny, E.: Large-scale document image retrieval and classification with runlength histograms and binary embeddings. Pattern Recognit 46(7), 1898\u20131905 (2013)","journal-title":"Pattern Recognit"},{"key":"225_CR21","doi-asserted-by":"crossref","unstructured":"Gordo, A., Rusi\u00f1ol, M., Karatzas, D., Bagdanov, A.: Document classification and page stream segmentation for digital mailroom applications. In: International Conference on Document Analysis and Recognition (2013)","DOI":"10.1109\/ICDAR.2013.128"},{"key":"225_CR22","doi-asserted-by":"crossref","unstructured":"Hamza, H., Bela\u00efd, Y., Bela\u00efd, A., Chaudhuri, B.: An end-to-end administrative document analysis system. In: Proceedings of the Fourteenth International Conference on Pattern Recognition, pp. 175\u2013182 (2008)","DOI":"10.1109\/DAS.2008.43"},{"key":"225_CR23","doi-asserted-by":"crossref","DOI":"10.1002\/0470090154","volume-title":"Classification, Parameter Estimation and State Estimation\u2014An Engineering Approach Using Matlab","author":"F Heijden van der","year":"2004","unstructured":"van der Heijden, F., Duin, R., de Ridder, D., Tax, D.: Classification, Parameter Estimation and State Estimation\u2014An Engineering Approach Using Matlab. Wiley, New York (2004)"},{"key":"225_CR24","doi-asserted-by":"crossref","unstructured":"H\u00e9roux, P., Diana, S., Ribert, A., Trupin, E.: Classification method study for automatic form class identification. In: Proceedings of the Fourteenth International Conference on Pattern Recognition, pp. 926\u2013928 (1998)","DOI":"10.1109\/ICPR.1998.711385"},{"key":"225_CR25","doi-asserted-by":"crossref","unstructured":"Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of the Twenty second Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 50\u201357 (1999)","DOI":"10.1145\/312624.312649"},{"key":"225_CR26","doi-asserted-by":"crossref","unstructured":"Meilender, T., Bela\u00efd, A.: Segmentation of continuous document flow by a modified backward-forward algorithm. In: Proceedings of the Document Recognition and Retrieval (2009)","DOI":"10.1117\/12.805646"},{"key":"225_CR27","unstructured":"Misue, K., Sakakibara, Y.: Building of a document classification tree by recursive optimization of keyword selection function. US Patent US5463773 A (1995)."},{"issue":"2","key":"225_CR28","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1109\/TIP.2004.840701","volume":"14","author":"F Odone","year":"2005","unstructured":"Odone, F., Barla, A., Verri, A.: Building kernels from binary strings for image matching. IEEE Trans. Image Process. 14(2), 169\u2013180 (2005)","journal-title":"IEEE Trans. Image Process."},{"key":"225_CR29","unstructured":"Porter, M.: Snowball: a language for stemming algorithms (2001)"},{"issue":"1","key":"225_CR30","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s10032-011-0151-y","volume":"15","author":"Y Rangoni","year":"2012","unstructured":"Rangoni, Y., Bela\u00efd, A., Vajda, S.: Labelling logical structures of document images using a dynamic perceptive neural network. Int. J. Document Anal. Recognit. 15(1), 45\u201355 (2012)","journal-title":"Int. J. Document Anal. Recognit."},{"key":"225_CR31","doi-asserted-by":"crossref","unstructured":"\u0158eh\u016f\u0159ek, R.: Subspace tracking for latent semantic analysis. In: Proceedings of the 33rd European Conference on Information Retrieval Research, pp. 289\u2013300 (2011)","DOI":"10.1007\/978-3-642-20161-5_29"},{"key":"225_CR32","unstructured":"Rusi\u00f1ol, M., Karatzas, D., Bagdanov, A.D., Llados, J.: Multipage document retrieval by textual and visual representations. In: International Conference on Pattern Recognition, pp. 521\u2013524 (2012)"},{"issue":"5","key":"225_CR33","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513\u2013523 (1988). doi: 10.1016\/0306-4573(88)90021-0","journal-title":"Inf. Process. Manag."},{"key":"225_CR34","doi-asserted-by":"crossref","unstructured":"Sarkar, P.: Image classification: classifying distributions of visual features. In: Proceedings of the International Conference on Pattern Recognition (2006)","DOI":"10.1109\/ICPR.2006.683"},{"key":"225_CR35","doi-asserted-by":"crossref","unstructured":"Schmidtler, M., Amtrup, J.: Automatic document separation: a combination of probabilistic classification and finite-state sequence modeling. In: Natural Language Processing and Text Mining, pp. 123\u2013144 (2006)","DOI":"10.1007\/978-1-84628-754-1_8"},{"issue":"1","key":"225_CR36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F Sebsatiani","year":"2002","unstructured":"Sebsatiani, F.: Machine learning in automated text categorization. J. ACM Comput. Surv. 34(1), 1\u201347 (2002)","journal-title":"J. ACM Comput. Surv."},{"issue":"4","key":"225_CR37","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1007\/PL00013566","volume":"3","author":"C Shin","year":"2001","unstructured":"Shin, C., Doermann, D., Rosenfeld, A.: Classification of document pages using structure-based features. Int. J. Document Anal. Recognit. 3(4), 232\u2013247 (2001)","journal-title":"Int. J. Document Anal. Recognit."},{"issue":"4","key":"225_CR38","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1016\/j.patcog.2010.09.014","volume":"44","author":"P Sidiropoulos","year":"2011","unstructured":"Sidiropoulos, P., Vrochidis, S., Kompatsiaris, I.: Content-based binary image retrieval using the adaptive hierarchical density histogram. Pattern Recognit. 44(4), 739\u2013750 (2011)","journal-title":"Pattern Recognit."},{"key":"225_CR39","doi-asserted-by":"crossref","unstructured":"Yang, Y., Liu, X.: A re-examination of text categorization methods. In: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 42\u201349 (1999)","DOI":"10.1145\/312624.312647"},{"key":"225_CR40","unstructured":"Yang, Y., Pederson, J.: A comparative study on feature selection in text categorization. In: Proceedings of the Fourteenth International Conference on Machine Learning, pp. 412\u2013420 (1997)"},{"key":"225_CR41","unstructured":"Young, S., Russell, N., Thornton, J.: Token passing: A simple conceptual model for connected speech recognition systems. Tech. Rep. CUED\/F-INFENG\/TR38, Cambridge University (1998)"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-014-0225-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-014-0225-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-014-0225-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T14:29:44Z","timestamp":1746282584000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-014-0225-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7,1]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["225"],"URL":"https:\/\/doi.org\/10.1007\/s10032-014-0225-8","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,1]]}}}