{"id":"https://openalex.org/W1983284692","doi":"https://doi.org/10.1007/pl00013569","title":"Transforming paper documents into XML format with WISDOM++","display_name":"Transforming paper documents into XML format with WISDOM++","publication_year":2001,"publication_date":"2001-08-01","ids":{"openalex":"https://openalex.org/W1983284692","doi":"https://doi.org/10.1007/pl00013569","mag":"1983284692"},"language":"en","primary_location":{"id":"doi:10.1007/pl00013569","doi":"https://doi.org/10.1007/pl00013569","is_oa":false,"landing_page_url":"https://doi.org/10.1007/pl00013569","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core","dongbi-c","jufo-1","norway-1","poland-100","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030643448","display_name":"Oronzo Altamura","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Oronzo Altamura","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy; e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy","e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy; e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035635558","display_name":"Floriana Esposito","orcid":"https://orcid.org/0000-0002-1075-3239","observed_orcids":["https://orcid.org/0000-0002-1075-3239"]},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Floriana Esposito","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy; e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy","e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy; e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035789137","display_name":"Donato Malerba","orcid":"https://orcid.org/0000-0001-8432-4608","observed_orcids":["https://orcid.org/0000-0001-8432-4608"]},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Donato Malerba","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy; e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy","e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy; e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, via Orabona 4, 70126 Bari, Italy","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"e-mail: {altamura,esposito,malerba}@di.uniba.it\n, , , , , , IT","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5561750"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":null,"fwci":8.5846,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.97649593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"4","issue":"1","first_page":"2","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12734","display_name":"Information Systems and Technology Applications","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/wisdom","display_name":"wisdom","score":0.8180000185966492},{"id":"https://openalex.org/keywords/document-image-classification","display_name":"document image classification","score":0.5789999961853027},{"id":"https://openalex.org/keywords/document-understanding","display_name":"document understanding","score":0.7929999828338623},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"document layout analysis","score":0.6669999957084656},{"id":"https://openalex.org/keywords/page-segmentation","display_name":"page segmentation","score":0.6899999976158142},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.8159999847412109},{"id":"https://openalex.org/keywords/document-image-preprocessing","display_name":"document preprocessing","score":0.6359999775886536},{"id":"https://openalex.org/keywords/web-document-retrieval","display_name":"web document retrieval","score":0.6930000185966492},{"id":"https://openalex.org/keywords/document-processing-systems","display_name":"document processing systems","score":0.4169999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8955675363540649},{"id":"https://openalex.org/C137441365","wikidata":"https://www.wikidata.org/wiki/Q7981054","display_name":"Well-formed document","level":5,"score":0.735878586769104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7304096817970276},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6847859025001526},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.6658743023872375},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.6253183484077454},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.6047222018241882},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5625297427177429},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5482925176620483},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5471991896629333},{"id":"https://openalex.org/C8595896","wikidata":"https://www.wikidata.org/wiki/Q577094","display_name":"Simple API for XML","level":5,"score":0.5297801494598389},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.5296919941902161},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.5016381740570068},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.48041510581970215},{"id":"https://openalex.org/C21761406","wikidata":"https://www.wikidata.org/wiki/Q8042330","display_name":"XML framework","level":3,"score":0.4768691956996918},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.44460174441337585},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.41626450419425964},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3787631094455719},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3461056351661682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25377988815307617},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13501831889152527},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.10999369621276855},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10742467641830444},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/pl00013569","doi":"https://doi.org/10.1007/pl00013569","is_oa":false,"landing_page_url":"https://doi.org/10.1007/pl00013569","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core","dongbi-c","jufo-1","norway-1","poland-100","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.2927","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.2927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.di.uniba.it/~malerba/publications/ijdar.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.33.4193","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.4193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.di.uniba.it/~malerba/publications/ijdar.pdf","raw_type":"text"},{"id":"pmh:oai:ricerca.uniba.it:11586/118849","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11586/118849","pdf_url":null,"source":{"id":"https://openalex.org/S4377196296","display_name":"CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5561750","host_organization_name":"University of Bari Aldo Moro","host_organization_lineage":["https://openalex.org/I5561750"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337253","display_name":"Instituto de Ciencias del Mar y Limnolog\u00eda, Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/040wdye98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W197527448","https://openalex.org/W1499683959","https://openalex.org/W1502424784","https://openalex.org/W1504694836","https://openalex.org/W1544407491","https://openalex.org/W1560626952","https://openalex.org/W1567193866","https://openalex.org/W1575597150","https://openalex.org/W1893130984","https://openalex.org/W2007680663","https://openalex.org/W2009737551","https://openalex.org/W2013866009","https://openalex.org/W2015432638","https://openalex.org/W2033661102","https://openalex.org/W2035305892","https://openalex.org/W2045018318","https://openalex.org/W2097217897","https://openalex.org/W2098470001","https://openalex.org/W2125055259","https://openalex.org/W2125276160","https://openalex.org/W2135085165","https://openalex.org/W2143680281","https://openalex.org/W2153554054","https://openalex.org/W2160245746","https://openalex.org/W2164727403","https://openalex.org/W2169402356","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W7099807345","https://openalex.org/W7098807036","https://openalex.org/W7005300220","https://openalex.org/W2116411409","https://openalex.org/W2105504191","https://openalex.org/W7096348878","https://openalex.org/W1514254660","https://openalex.org/W2134590793","https://openalex.org/W7008820915","https://openalex.org/W4407538740"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
