{"id":"https://openalex.org/W2129505588","doi":"https://doi.org/10.1109/icme.2003.1220882","title":"Extracting anchorable information units from PDF files","display_name":"Extracting anchorable information units from PDF files","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2129505588","doi":"https://doi.org/10.1109/icme.2003.1220882","mag":"2129505588"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1220882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5048043105","display_name":"Amit Chakraborty","orcid":"https://orcid.org/0000-0003-4161-1994"},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"A. Chakraborty","raw_affiliation_strings":["Siemens Corporate Research, Inc., USA","Siemens Corp. Res. Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Siemens Corporate Research, Inc., USA","institution_ids":["https://openalex.org/I4210137693"]},{"raw_affiliation_string":"Siemens Corp. Res. Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005568062","display_name":"P. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Liu","raw_affiliation_strings":["Siemens Corporate Research, Inc., USA","Siemens Corp. Res. Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Siemens Corporate Research, Inc., USA","institution_ids":["https://openalex.org/I4210137693"]},{"raw_affiliation_string":"Siemens Corp. Res. Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025630555","display_name":"Liang H. Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Hsu","raw_affiliation_strings":["Siemens Corporate Research, Inc., USA","Siemens Corp. Res. Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Siemens Corporate Research, Inc., USA","institution_ids":["https://openalex.org/I4210137693"]},{"raw_affiliation_string":"Siemens Corp. Res. Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I4210137693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048043105"],"corresponding_institution_ids":["https://openalex.org/I4210137693"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.19397198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"54","issue":null,"first_page":"I","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9890000224113464,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8808406591415405},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.7286651730537415},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.7217636704444885},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.7213632464408875},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6461593508720398},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5974448323249817},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5456475019454956},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5438322424888611},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5393694639205933},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5073766112327576},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45825329422950745},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44965410232543945},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44459986686706543},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.43465206027030945},{"id":"https://openalex.org/keywords/electronic-document","display_name":"Electronic document","score":0.42674195766448975},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.4206019341945648},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.300041526556015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2789953649044037},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.2027984857559204},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19970214366912842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808406591415405},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.7286651730537415},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7217636704444885},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7213632464408875},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6461593508720398},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5974448323249817},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5456475019454956},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5438322424888611},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5393694639205933},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5073766112327576},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45825329422950745},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44965410232543945},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44459986686706543},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.43465206027030945},{"id":"https://openalex.org/C2778315425","wikidata":"https://www.wikidata.org/wiki/Q694975","display_name":"Electronic document","level":2,"score":0.42674195766448975},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.4206019341945648},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.300041526556015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2789953649044037},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.2027984857559204},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19970214366912842},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2003.1220882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2052721056","https://openalex.org/W2102545463","https://openalex.org/W2146233719","https://openalex.org/W2264536321","https://openalex.org/W4285719527","https://openalex.org/W6602893997","https://openalex.org/W6681727322"],"related_works":["https://openalex.org/W2351590241","https://openalex.org/W2218402054","https://openalex.org/W2096747878","https://openalex.org/W4383988422","https://openalex.org/W2168844671","https://openalex.org/W4306157992","https://openalex.org/W2244000356","https://openalex.org/W2352804407","https://openalex.org/W1971234693","https://openalex.org/W2541388296"],"abstract_inverted_index":{"Document":[0],"processing":[1,182],"and":[2,21,37,50,140,176],"understanding":[3],"is":[4,149],"important":[5],"for":[6,68,111,169],"a":[7,65,178],"variety":[8,179],"of":[9,16,34,81,142,154,166,180],"applications":[10],"such":[11],"as":[12,76],"office":[13],"automation,":[14],"creation":[15],"electronic":[17,60,120],"manuals,":[18],"online":[19],"documentation":[20],"annotation":[22],"etc.":[23],"The":[24,101],"first":[25,171],"step":[26],"towards":[27],"this":[28],"process":[29],"often":[30],"involves":[31],"the":[32,40,52,128,134,138,143,147,152,164,172],"extraction":[33,135,168],"relevant":[35],"keywords":[36],"phrases":[38],"from":[39,78],"documents":[41,108,117,129],"so":[42,54],"that":[43,55],"they":[44],"can":[45,57],"be":[46,90],"automatically":[47],"hyperlinked":[48],"within":[49,118],"outside":[51],"document":[53,83,121],"we":[56],"create":[58],"an":[59,94,119,155],"document.":[61],"This":[62],"paper":[63],"describes":[64],"novel":[66],"method":[67],"extracting":[69],"anchorable":[70],"information":[71],"units":[72],"(AIUs),":[73],"also":[74],"known":[75],"hotspots":[77],"any":[79],"type":[80],"portable":[82],"format":[84],"(PDF)":[85],"files,":[86],"which":[87],"may":[88],"either":[89,93],"created":[91],"using":[92],"editor":[95],"or":[96],"by":[97],"scanning":[98],"in":[99],"documents.":[100],"AIUs":[102],"are":[103,130,145,174,184],"used":[104,131],"to":[105,132],"make":[106],"these":[107],"more":[109],"intelligent":[110],"content":[112,148],"cross-referencing":[113],"to/from":[114],"related":[115],"multimedia":[116],"publishing":[122],"environment.":[123],"Domain":[124],"specific":[125],"knowledge":[126],"about":[127],"aid":[133],"process.":[136],"Once":[137],"location":[139],"extent":[141],"texts":[144],"found,":[146],"extracted":[150,175],"through":[151],"use":[153],"optical":[156],"character":[157],"recognition":[158],"(OCR)":[159],"software":[160],"if":[161],"necessary.":[162],"For":[163],"case":[165],"object":[167],"highlighting,":[170],"images":[173],"then":[177],"image":[181],"algorithms":[183],"applied.":[185]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
