{"id":"https://openalex.org/W2157856440","doi":"https://doi.org/10.1145/1577802.1577809","title":"Combined script and page orientation estimation using the Tesseract OCR engine","display_name":"Combined script and page orientation estimation using the Tesseract OCR engine","publication_year":2009,"publication_date":"2009-07-25","ids":{"openalex":"https://openalex.org/W2157856440","doi":"https://doi.org/10.1145/1577802.1577809","mag":"2157856440"},"language":"en","primary_location":{"id":"doi:10.1145/1577802.1577809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1577802.1577809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Multilingual OCR","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103778960","display_name":"Ranjith Unnikrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ranjith Unnikrishnan","raw_affiliation_strings":["Google Inc., Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110962620","display_name":"Ray Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ray Smith","raw_affiliation_strings":["Google Inc., Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.5361,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.65096839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9914000034332275,"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":0.9904999732971191,"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":0.644219160079956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6243385076522827},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5458403825759888},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4349600076675415},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38752394914627075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3816331624984741},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3280012011528015},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13886556029319763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.644219160079956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243385076522827},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5458403825759888},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4349600076675415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38752394914627075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3816331624984741},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3280012011528015},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13886556029319763}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1577802.1577809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1577802.1577809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Multilingual OCR","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.197","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/35506.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W87694687","https://openalex.org/W1560318390","https://openalex.org/W2001642682","https://openalex.org/W2100607392","https://openalex.org/W2104707377","https://openalex.org/W2119123874","https://openalex.org/W2121979056","https://openalex.org/W2129265797","https://openalex.org/W2165628625","https://openalex.org/W2626914210"],"related_works":["https://openalex.org/W2292997772","https://openalex.org/W170731741","https://openalex.org/W2055970094","https://openalex.org/W4377970376","https://openalex.org/W4318615658","https://openalex.org/W240009282","https://openalex.org/W2904601236","https://openalex.org/W2765524311","https://openalex.org/W4301510055","https://openalex.org/W2168005840"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,42,92,98,124],"simple":[4],"but":[5],"effective":[6],"algorithm":[7],"to":[8,40,54,74],"estimate":[9,78],"the":[10,17,49,58,65,68,76,86,89,128],"script":[11,31],"and":[12,38,67,82,106],"dominant":[13],"page":[14,80,111],"orientation":[15,63,81],"of":[16,26,64,79,88,94,101,108,116,127],"text":[18,37],"contained":[19],"in":[20,57,103,123],"an":[21],"image.":[22],"A":[23,113],"candidate":[24],"set":[25,100],"shape":[27,44],"classes":[28],"for":[29,60],"each":[30,61],"is":[32,51],"generated":[33],"using":[34],"synthetically":[35],"rendered":[36],"used":[39,73],"train":[41],"fast":[43],"classifier.":[45],"At":[46],"run":[47],"time,":[48],"classifier":[50],"applied":[52],"independently":[53],"connected":[55],"components":[56],"image":[59],"possible":[62,110],"component,":[66],"accumulated":[69],"confidence":[70],"scores":[71],"are":[72],"determine":[75],"best":[77],"script.":[83],"Results":[84],"demonstrate":[85],"effectiveness":[87],"approach":[90],"on":[91],"dataset":[93],"1846":[95],"documents":[96],"containing":[97],"diverse":[99],"images":[102],"14":[104],"scripts":[105],"any":[107],"four":[109],"orientations.":[112],"C++":[114],"implementation":[115],"this":[117],"work":[118],"will":[119],"be":[120],"made":[121],"available":[122],"future":[125],"release":[126],"open-source":[129],"Tesseract":[130],"OCR":[131],"engine":[132],"[1].":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}