{"id":"https://openalex.org/W770111601","doi":"https://doi.org/10.1007/s10032-015-0247-x","title":"Integrating natural language processing with image document analysis: what we learned from two real-world applications","display_name":"Integrating natural language processing with image document analysis: what we learned from two real-world applications","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W770111601","doi":"https://doi.org/10.1007/s10032-015-0247-x","mag":"770111601"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-015-0247-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10032-015-0247-x","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,"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 (IJDAR)","raw_type":"journal-article"},"type":"article","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/A5037095141","display_name":"Jinying Chen","orcid":"https://orcid.org/0000-0001-7259-4301"},"institutions":[{"id":"https://openalex.org/I166722992","display_name":"University of Massachusetts Chan Medical School","ror":"https://ror.org/0464eyp60","country_code":"US","type":"education","lineage":["https://openalex.org/I166722992"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinying Chen","raw_affiliation_strings":["Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA","Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA","institution_ids":["https://openalex.org/I166722992"]},{"raw_affiliation_string":"Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, USA#TAB#","institution_ids":["https://openalex.org/I166722992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108504544","display_name":"Huaigu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaigu Cao","raw_affiliation_strings":["Department of Speech, Language and Multimedia, Raytheon BBN Technologies, Cambridge, MA, USA","Department of Speech, Language and Multimedia, Raytheon BBN Technologies, Cambridge, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Speech, Language and Multimedia, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Department of Speech, Language and Multimedia, Raytheon BBN Technologies, Cambridge, USA#TAB#","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Premkumar Natarajan","raw_affiliation_strings":["Information Sciences Institute, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292, USA","Information Sciences Institute, Marina del Rey, USA 90292#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292, USA","institution_ids":[]},{"raw_affiliation_string":"Information Sciences Institute, Marina del Rey, USA 90292#TAB#","institution_ids":["https://openalex.org/I2801204180"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037095141"],"corresponding_institution_ids":["https://openalex.org/I166722992"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.4741,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.70783867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"3","first_page":"235","last_page":"247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.995199978351593,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8467496633529663},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7839584350585938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6543097496032715},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6469467878341675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6342449188232422},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5221538543701172},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5099848508834839},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5011882781982422},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.48100098967552185},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.47388097643852234},{"id":"https://openalex.org/keywords/intelligent-character-recognition","display_name":"Intelligent character recognition","score":0.4634535014629364},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.45767921209335327},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.42597317695617676},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.42455852031707764},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3308042883872986},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.1192350685596466},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09533098340034485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467496633529663},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7839584350585938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6543097496032715},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6469467878341675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6342449188232422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5221538543701172},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5099848508834839},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5011882781982422},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.48100098967552185},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.47388097643852234},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.4634535014629364},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.45767921209335327},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.42597317695617676},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.42455852031707764},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3308042883872986},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.1192350685596466},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09533098340034485},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10032-015-0247-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10032-015-0247-x","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,"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 (IJDAR)","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G8508159280","display_name":null,"funder_award_id":"HR0011-08-C-0004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W28518826","https://openalex.org/W90695545","https://openalex.org/W1490831147","https://openalex.org/W1528022942","https://openalex.org/W1586405805","https://openalex.org/W1766606308","https://openalex.org/W1787547118","https://openalex.org/W1796186776","https://openalex.org/W1985720554","https://openalex.org/W1999389561","https://openalex.org/W2002070877","https://openalex.org/W2002342963","https://openalex.org/W2003859078","https://openalex.org/W2008973672","https://openalex.org/W2009389931","https://openalex.org/W2015591846","https://openalex.org/W2027257218","https://openalex.org/W2028252982","https://openalex.org/W2051434435","https://openalex.org/W2084294137","https://openalex.org/W2091966695","https://openalex.org/W2096355136","https://openalex.org/W2097584131","https://openalex.org/W2110462621","https://openalex.org/W2111417594","https://openalex.org/W2113540630","https://openalex.org/W2121764873","https://openalex.org/W2122511433","https://openalex.org/W2129511053","https://openalex.org/W2139727660","https://openalex.org/W2140281218","https://openalex.org/W2140343992","https://openalex.org/W2141099517","https://openalex.org/W2144533356","https://openalex.org/W2147880316","https://openalex.org/W2153817962","https://openalex.org/W2156515921","https://openalex.org/W2161274063","https://openalex.org/W2163374925","https://openalex.org/W2166905217","https://openalex.org/W2167609840","https://openalex.org/W2250978584","https://openalex.org/W2426479676","https://openalex.org/W2541478194","https://openalex.org/W2594610113","https://openalex.org/W3196919033","https://openalex.org/W4285719527","https://openalex.org/W6600674394"],"related_works":["https://openalex.org/W2218402054","https://openalex.org/W4384296853","https://openalex.org/W2168844671","https://openalex.org/W954954433","https://openalex.org/W4320027814","https://openalex.org/W2183182603","https://openalex.org/W2188613573","https://openalex.org/W3128781766","https://openalex.org/W3044341113","https://openalex.org/W3035903760"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
