{"id":"https://openalex.org/W2593447511","doi":"https://doi.org/10.1109/escience.2016.7870884","title":"Cooperative human-machine data extraction from biological collections","display_name":"Cooperative human-machine data extraction from biological collections","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2593447511","doi":"https://doi.org/10.1109/escience.2016.7870884","mag":"2593447511"},"language":"en","primary_location":{"id":"doi:10.1109/escience.2016.7870884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2016.7870884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 12th International Conference on e-Science (e-Science)","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/A5027673766","display_name":"Icaro Alzuru","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Icaro Alzuru","raw_affiliation_strings":["Advanced Computing and Information Systems(ACIS), Laboratory University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Computing and Information Systems(ACIS), Laboratory University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003262238","display_name":"Andr\u00e9a Matsunaga","orcid":"https://orcid.org/0000-0001-9036-5895"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Matsunaga","raw_affiliation_strings":["Advanced Computing and Information Systems(ACIS), Laboratory University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Computing and Information Systems(ACIS), Laboratory University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086302230","display_name":"Maur\u00edcio Tsugawa","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mauricio Tsugawa","raw_affiliation_strings":["Advanced Computing and Information Systems(ACIS), Laboratory University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Computing and Information Systems(ACIS), Laboratory University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003181544","display_name":"J.A.B. Fortes","orcid":"https://orcid.org/0000-0001-8870-5205"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose A. B. Fortes","raw_affiliation_strings":["Advanced Computing and Information Systems(ACIS), Laboratory University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Computing and Information Systems(ACIS), Laboratory University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027673766"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.7911,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86374559,"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":"41","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13362","display_name":"Slime Mold and Myxomycetes Research","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9696999788284302,"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":0.8446117639541626},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7702299356460571},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7556803226470947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7315903902053833},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6253500580787659},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.5117766261100769},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47272390127182007},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.449399471282959},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44832199811935425},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42993393540382385},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37678930163383484},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22875577211380005},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13515949249267578},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1252211332321167},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12155494093894958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8446117639541626},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7702299356460571},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7556803226470947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7315903902053833},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6253500580787659},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.5117766261100769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47272390127182007},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.449399471282959},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44832199811935425},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42993393540382385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37678930163383484},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22875577211380005},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13515949249267578},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1252211332321167},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12155494093894958},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/escience.2016.7870884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2016.7870884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 12th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1030645745","https://openalex.org/W2001642682","https://openalex.org/W2001848404","https://openalex.org/W2008459216","https://openalex.org/W2013076999","https://openalex.org/W2058153205","https://openalex.org/W2060580591","https://openalex.org/W2133807961","https://openalex.org/W2327209116","https://openalex.org/W2434079478","https://openalex.org/W2580911115","https://openalex.org/W2616747538","https://openalex.org/W4300601563","https://openalex.org/W6650820226","https://openalex.org/W6679983794"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114","https://openalex.org/W4286908577"],"abstract_inverted_index":{"Historical":[0],"data":[1,92,114],"sources,":[2],"like":[3],"medical":[4],"records":[5],"or":[6,167],"biological":[7],"collections,":[8],"consist":[9],"of":[10,20,54,106,176],"unstructured":[11],"heterogeneous":[12],"content:":[13],"handwritten":[14],"text,":[15],"different":[16,189],"sizes":[17],"and":[18,22,29,43,78,87,96,108,117,131,182,207,222,226],"types":[19],"fonts,":[21],"text":[23,152],"overlapped":[24],"with":[25,179],"lines,":[26],"images,":[27,178],"stamps,":[28],"sketches.":[30],"The":[31,51,174],"information":[32],"these":[33,55],"documents":[34,57],"can":[35,47,143,165],"provide":[36],"is":[37,58,185],"important,":[38],"from":[39,49],"a":[40,59,122,213],"historical":[41,56],"perspective":[42],"mainly":[44],"because":[45],"we":[46,127],"learn":[48],"it.":[50],"automatic":[52],"digitization":[53,175],"complex":[60],"machine":[61,109],"learning":[62],"process":[63],"that":[64,103],"usually":[65],"produces":[66],"poor":[67],"results,":[68],"requiring":[69],"costly":[70],"interventions":[71],"by":[72,147,156],"experts,":[73],"who":[74],"have":[75],"to":[76,121,159],"transcribe":[77],"interpret":[79],"the":[80,104,162,171,192,209],"content.":[81],"This":[82],"paper":[83],"describes":[84],"hybrid":[85],"(Human-":[86],"Machine-Intelligent)":[88],"workflows":[89],"for":[90],"scientific":[91],"extraction,":[93],"combining":[94],"machine-learning":[95],"crowdsourcing":[97],"software":[98],"elements.":[99],"Our":[100],"results":[101],"demonstrate":[102],"mix":[105],"human":[107],"processes":[110],"has":[111],"advantages":[112],"in":[113,220],"extraction":[115],"time":[116,164],"quality,":[118],"when":[119,151],"compared":[120],"machine-only":[123,210],"workflow.":[124],"More":[125],"specifically,":[126],"show":[128],"how":[129],"OCRopus":[130],"Tesseract,":[132],"two":[133],"widely":[134],"used":[135],"open":[136],"source":[137],"Optical":[138],"Character":[139],"Recognition":[140],"(OCR)":[141],"tools,":[142],"improve":[144],"their":[145],"accuracy":[146],"more":[148],"than":[149],"42%,":[150],"areas":[153],"are":[154],"cropped":[155,199,204],"humans":[157],"prior":[158],"OCR,":[160],"while":[161],"total":[163],"increase":[166],"decrease":[168],"depending":[169],"on":[170],"OCR":[172],"selection.":[173],"400":[177],"Entomology,":[180],"Bryophyte,":[181],"Lichen":[183],"specimens,":[184],"evaluated":[186],"following":[187],"four":[188],"approaches:":[190],"processing":[191,197,202],"whole":[193],"specimen":[194],"image":[195],"(machine-only),":[196],"crowd":[198,203],"labels":[200],"(hybrid),":[201,206],"fields":[205],"cleaning":[208],"output.":[211],"As":[212],"secondary":[214],"result,":[215],"our":[216],"experiments":[217],"reveal":[218],"differences":[219],"speed":[221],"quality":[223],"between":[224],"Tesseract":[225],"OCRopus.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}