{"id":"https://openalex.org/W2025414155","doi":"https://doi.org/10.1145/1410140.1410197","title":"An optical character recognition approach to qualifying thresholding algorithms","display_name":"An optical character recognition approach to qualifying thresholding algorithms","publication_year":2008,"publication_date":"2008-09-16","ids":{"openalex":"https://openalex.org/W2025414155","doi":"https://doi.org/10.1145/1410140.1410197","mag":"2025414155"},"language":"en","primary_location":{"id":"doi:10.1145/1410140.1410197","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1410140.1410197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM symposium on Document engineering","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/A5091740796","display_name":"Margaret Sturgill","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Margaret Sturgill","raw_affiliation_strings":["Hewlett Packard Labs, Fort Collins, CO, USA","Hewlett Packard Laboratories, Fort Collins, CO, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Laboratories, Fort Collins, CO, USA#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022519243","display_name":"Steven J. Simske","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven J. Simske","raw_affiliation_strings":["Hewlett Packard Labs, Fort Collins, CO, USA","Hewlett Packard Laboratories, Fort Collins, CO, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Laboratories, Fort Collins, CO, USA#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091740796"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":2.1071,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.878234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9995999932289124,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9995999932289124,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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":0.9991999864578247,"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/thresholding","display_name":"Thresholding","score":0.8924169540405273},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.8081107139587402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7824005484580994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6752520203590393},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6184120774269104},{"id":"https://openalex.org/keywords/raster-graphics","display_name":"Raster graphics","score":0.6110515594482422},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5872706174850464},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5460439324378967},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5450847148895264},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5179864168167114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5151716470718384},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5006647109985352},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.47843673825263977},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4293905794620514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09046906232833862}],"concepts":[{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.8924169540405273},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.8081107139587402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824005484580994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6752520203590393},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6184120774269104},{"id":"https://openalex.org/C181844469","wikidata":"https://www.wikidata.org/wiki/Q182270","display_name":"Raster graphics","level":2,"score":0.6110515594482422},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5872706174850464},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5460439324378967},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5450847148895264},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5179864168167114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5151716470718384},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5006647109985352},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.47843673825263977},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4293905794620514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09046906232833862},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1410140.1410197","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1410140.1410197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W56465887","https://openalex.org/W2018759723","https://openalex.org/W2027091505","https://openalex.org/W2087079057","https://openalex.org/W2133059825"],"related_works":["https://openalex.org/W2138983844","https://openalex.org/W1968965685","https://openalex.org/W2129389683","https://openalex.org/W2012792772","https://openalex.org/W2356573839","https://openalex.org/W179947483","https://openalex.org/W2111883783","https://openalex.org/W2009028679","https://openalex.org/W2357424838","https://openalex.org/W2356903262"],"abstract_inverted_index":{"Pre-processing":[0],"for":[1,42,111,140,148],"raster":[2],"image":[3,9],"based":[4],"document":[5],"segmentation":[6],"begins":[7],"with":[8],"thresholding,":[10],"which":[11,43,61],"is":[12,49],"a":[13,37,96,120,137],"binarization":[14],"process":[15],"separating":[16],"foreground":[17],"from":[18],"background.":[19],"In":[20],"this":[21,133],"paper,":[22],"we":[23,77],"compare":[24],"an":[25,56,63,92,103,113],"existing":[26,29,44],"(Otsu),":[27],"modified":[28],"(Kittler-Illingworth)":[30],"and":[31,143],"simple":[32],"peak-based":[33],"thresholding":[34],"approach":[35,134],"on":[36],"set":[38,122],"of":[39,55,72,82,98,119,123],"982":[40],"documents":[41],"ground":[45,124,151],"truth":[46],"(full":[47],"text)":[48],"available.":[50],"We":[51,89],"use":[52],"the":[53,73,87,109,117,146],"output":[54],"open":[57],"source":[58],"OCR":[59],"engine":[60],"incorporates":[62],"adaptive/dynamic":[64],"thresholder":[65,100,115,141],"that":[66,132],"can":[67],"be":[68],"bypassed":[69],"by":[70],"one":[71],"three":[74,84],"global":[75],"thresholds":[76],"tested.":[78],"This":[79],"allowed":[80],"comparison":[81,142],"these":[83],"approaches":[85],"in":[86,116],"aggregate.":[88],"then":[90],"used":[91],"independently-generated":[93],"dictionary":[94],"as":[95],"means":[97,110,139],"characterizing":[99],"efficacy.":[101],"Such":[102],"approach,":[104],"if":[105],"successful,":[106],"will":[107],"provide":[108,136],"selecting":[112],"optimal":[114],"absence":[118],"large":[121],"truthed":[125],"documents.":[126],"Our":[127],"preliminary":[128],"findings":[129],"here":[130],"indicate":[131],"may":[135],"reliable":[138],"eventually":[144],"preclude":[145],"need":[147],"time-intensive":[149],"human":[150],"truthing.":[152]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}