{"id":"https://openalex.org/W2139795183","doi":"https://doi.org/10.1109/dial.2004.1263236","title":"Document digitization technology and its application for digital library in China","display_name":"Document digitization technology and its application for digital library in China","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2139795183","doi":"https://doi.org/10.1109/dial.2004.1263236","mag":"2139795183"},"language":"en","primary_location":{"id":"doi:10.1109/dial.2004.1263236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings.","raw_type":"proceedings-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/A5019552689","display_name":"Xiaoqing Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Ding","raw_affiliation_strings":["Department of Electronic Engineering, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005838535","display_name":"Wen Di","orcid":"https://orcid.org/0000-0003-4007-3856"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wen","raw_affiliation_strings":["Department of Electronic Engineering, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076442506","display_name":"Liangrui Peng","orcid":"https://orcid.org/0000-0001-7793-1039"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangrui Peng","raw_affiliation_strings":["Department of Electronic Engineering, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101489952","display_name":"Changsong Liu","orcid":"https://orcid.org/0000-0002-1387-7499"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsong Liu","raw_affiliation_strings":["Department of Electronic Engineering, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.105,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80269668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9866999983787537,"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":0.9779999852180481,"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/digitization","display_name":"Digitization","score":0.9262294769287109},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7465782165527344},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6508145332336426},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6409366130828857},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5126935243606567},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4747790992259979},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.422793447971344},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42225590348243713},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.419779896736145},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34774085879325867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2684251666069031},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16912439465522766},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15232780575752258},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1467246115207672}],"concepts":[{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.9262294769287109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465782165527344},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6508145332336426},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6409366130828857},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5126935243606567},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4747790992259979},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.422793447971344},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42225590348243713},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.419779896736145},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34774085879325867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2684251666069031},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16912439465522766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15232780575752258},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1467246115207672},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dial.2004.1263236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1974753588","https://openalex.org/W2051666937","https://openalex.org/W2084525555","https://openalex.org/W2118352015","https://openalex.org/W2150052143","https://openalex.org/W6677499954"],"related_works":["https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4251369848","https://openalex.org/W2746392713","https://openalex.org/W2163748916","https://openalex.org/W4385509036","https://openalex.org/W3167700301","https://openalex.org/W2002966468","https://openalex.org/W2368778223"],"abstract_inverted_index":{"We":[0,17],"introduce":[1],"the":[2,31,39,74,78,89,105,116,120,123,132,144],"research":[3,41],"of":[4,23,93,98,115],"document":[5,24,80,108,125],"digitization":[6,25,81,146],"technology":[7],"and":[8,28,48,65,72,83,112],"its":[9],"applications":[10,92,136],"for":[11],"constructing":[12],"digital":[13,101,150],"libraries":[14],"in":[15,51,148],"China.":[16],"focus":[18],"on":[19,43],"two":[20,96],"major":[21],"objectives":[22],"technologies:":[26],"performance":[27,60],"efficiency.":[29,90],"Taking":[30],"most":[32],"representative":[33],"TH-OCR":[34,94],"product":[35],"as":[36],"an":[37],"example,":[38],"up-to-date":[40],"achievements":[42],"both":[44],"kernel":[45,56],"OCR":[46,127],"technologies":[47,50,57,76,140],"peripheral":[49,75],"China":[52],"are":[53],"presented.":[54],"The":[55,91],"include":[58,77],"high":[59],"multilingual":[61],"(Chinese,":[62],"Japanese,":[63],"Korean":[64],"English)":[66],"text":[67,111,129],"recognition,":[68],"layout":[69,113],"analysis,":[70],"understanding":[71],"reconstruction;":[73],"network":[79],"workflow":[82],"intelligent":[84],"proofreading,":[85],"which":[86],"greatly":[87,142],"improve":[88],"has":[95],"types":[97],"final":[99],"output":[100,128],"documents,":[102],"one":[103],"is":[104,122],"reconstructed":[106],"electronic":[107],"with":[109,126],"full":[110],"information":[114],"original":[117],"paper-based":[118],"document,":[119],"other":[121],"multilevel":[124],"layer":[130],"under":[131],"image":[133],"layer.":[134],"Numerous":[135],"indicate":[137],"that":[138],"current":[139],"can":[141],"facilitate":[143],"mass-volume":[145],"labour":[147],"building":[149],"library":[151],"infrastructure.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
