{"id":"https://openalex.org/W2033547624","doi":"https://doi.org/10.1145/1655925.1656103","title":"Converting PDF to HTML approach based on text detection","display_name":"Converting PDF to HTML approach based on text detection","publication_year":2009,"publication_date":"2009-11-24","ids":{"openalex":"https://openalex.org/W2033547624","doi":"https://doi.org/10.1145/1655925.1656103","mag":"2033547624"},"language":"en","primary_location":{"id":"doi:10.1145/1655925.1656103","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1655925.1656103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human","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":null,"display_name":"Deliang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Deliang Jiang","raw_affiliation_strings":["Zhejiang University, HangZhou, China","Zhejiang university, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang university, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026311099","display_name":"Xiaohu Yang","orcid":"https://orcid.org/0000-0003-3997-4606"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohu Yang","raw_affiliation_strings":["ZheJiang University, HangZhou, China","Zhejiang university, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"ZheJiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang university, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.5526,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88528585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"982","last_page":"985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9628000259399414,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8192042112350464},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7460471987724304},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5405515432357788},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4793970584869385},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.4712938368320465},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4521116316318512},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.4136267900466919},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3965466320514679},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.31340688467025757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22582802176475525},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.12795594334602356},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09713742136955261},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09252074360847473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192042112350464},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7460471987724304},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5405515432357788},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4793970584869385},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.4712938368320465},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4521116316318512},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.4136267900466919},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3965466320514679},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.31340688467025757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22582802176475525},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.12795594334602356},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09713742136955261},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09252074360847473},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1655925.1656103","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1655925.1656103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W141724566","https://openalex.org/W2121061496","https://openalex.org/W2142809404","https://openalex.org/W2149546672","https://openalex.org/W3023264106"],"related_works":["https://openalex.org/W4255056669","https://openalex.org/W2124842464","https://openalex.org/W2382657549","https://openalex.org/W4376877853","https://openalex.org/W75565505","https://openalex.org/W4214847518","https://openalex.org/W3005052110","https://openalex.org/W3200575725","https://openalex.org/W4242732953","https://openalex.org/W2774879466"],"abstract_inverted_index":{"Converting":[0],"PDF":[1,26,42,63,68],"document":[2,5,27,43,64,69],"to":[3,28,70],"HTML":[4,71],"with":[6],"the":[7,20,37,41,45,50,58,62,67],"same":[8],"layout":[9,59],"format":[10],"is":[11,23],"a":[12,53],"very":[13],"important":[14],"and":[15,32,65],"interesting":[16],"research":[17],"problem.":[18],"After":[19],"conversion,":[21],"it":[22],"easy":[24],"for":[25],"be":[29],"browsed":[30],"online":[31],"information":[33,60],"extracted.":[34],"Based":[35],"on":[36],"extraction":[38],"result":[39],"of":[40,44,61],"open":[46],"source":[47],"tool":[48],"PDFBox,":[49],"paper":[51],"described":[52],"method":[54],"that":[55],"can":[56],"detect":[57],"convert":[66],"page":[72],"effectively.":[73]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
