{"id":"https://openalex.org/W2142205427","doi":"https://doi.org/10.1109/icdar.2015.7333920","title":"Unsupervised feature learning for optical character recognition","display_name":"Unsupervised feature learning for optical character recognition","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2142205427","doi":"https://doi.org/10.1109/icdar.2015.7333920","mag":"2142205427"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2015.7333920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","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/A5003803425","display_name":"D. K. Sahu","orcid":"https://orcid.org/0000-0002-6688-0800"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Devendra K Sahu","raw_affiliation_strings":["Center for Visual Information Technology, IIIT Hyderabad, India","Center for Visual Information Technology, IIIT, Hyderabad, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Visual Information Technology, IIIT Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Center for Visual Information Technology, IIIT, Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. V. Jawahar","raw_affiliation_strings":["Center for Visual Information Technology, IIIT Hyderabad, India","Center for Visual Information Technology, IIIT, Hyderabad, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Visual Information Technology, IIIT Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Center for Visual Information Technology, IIIT, Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003803425"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.5615,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.75147356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"abs 1206 5538","issue":null,"first_page":"1041","last_page":"1045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition 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/T10601","display_name":"Handwritten Text Recognition 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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.982200026512146,"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/T11309","display_name":"Music and Audio Processing","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.6992141008377075},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6747936606407166},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6080475449562073},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5879636406898499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5838145017623901},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.549192488193512},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5320932269096375},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5220223069190979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49854063987731934},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.463374525308609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3484177589416504},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0737241804599762},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07195362448692322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992141008377075},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6747936606407166},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6080475449562073},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5879636406898499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5838145017623901},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.549192488193512},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5320932269096375},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5220223069190979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49854063987731934},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.463374525308609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3484177589416504},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0737241804599762},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07195362448692322},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":2,"locations":[{"id":"doi:10.1109/icdar.2015.7333920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.7802","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.7802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cvit.iiit.ac.in/papers/Devendra2015Unsupervised.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2015896468","https://openalex.org/W2055555960","https://openalex.org/W2060580591","https://openalex.org/W2072128103","https://openalex.org/W2116064496","https://openalex.org/W2116825644","https://openalex.org/W2121380873","https://openalex.org/W2122585011","https://openalex.org/W2127141656","https://openalex.org/W2153182373","https://openalex.org/W2163605009","https://openalex.org/W2163922914","https://openalex.org/W2474855605","https://openalex.org/W4231109964","https://openalex.org/W6683994600","https://openalex.org/W6684191040","https://openalex.org/W6721014087"],"related_works":["https://openalex.org/W2171915408","https://openalex.org/W2695951553","https://openalex.org/W42449913","https://openalex.org/W2775464024","https://openalex.org/W2592385986","https://openalex.org/W2354193593","https://openalex.org/W1661159222","https://openalex.org/W3093564170","https://openalex.org/W2118744957","https://openalex.org/W2899683012"],"abstract_inverted_index":{"Most":[0],"of":[1,12,24,32,38,68,76,93,98,124,170],"the":[2,30,36,73,81,91,109,114,121,125,146,171],"popular":[3],"optical":[4],"character":[5,21],"recognition":[6,45,149],"(OCR)":[7],"architectures":[8],"use":[9,57,143],"a":[10,16,104,136],"set":[11,97],"handcrafted":[13],"features":[14,34,59,99,112,134,163],"and":[15,83,142],"powerful":[17],"classifier":[18],"for":[19,35,100,103],"isolated":[20],"classification.":[22],"Success":[23,67],"these":[25,33,69,77,161],"methods":[26,56,70],"often":[27],"depend":[28,71],"on":[29,47,72,155],"suitability":[31],"language":[37,84,110],"interest.":[39],"In":[40,86,129,159],"recent":[41],"years,":[42],"whole":[43],"word":[44],"based":[46,148],"Recurrent":[48],"Neural":[49],"Networks":[50],"(RNN)":[51],"has":[52],"gained":[53],"popularity.":[54],"These":[55],"simple":[58],"such":[60],"as":[61],"raw":[62],"pixel":[63],"values":[64],"or":[65],"profiles.":[66],"learning":[74,94],"capabilities":[75],"networks":[78],"to":[79],"encode":[80],"script":[82],"information.":[85],"this":[87,130],"work,":[88,131],"we":[89,132],"investigate":[90],"possibility":[92],"an":[95],"appropriate":[96],"designing":[101],"OCR":[102],"specific":[105,111],"language.":[106],"We":[107,151],"learn":[108,133],"from":[113],"data":[115],"with":[116,145],"no":[117],"supervision.":[118],"This":[119],"enables":[120],"seamless":[122],"adaptation":[123],"architecture":[126],"across":[127],"languages.":[128,158],"using":[135],"stacked":[137],"Restricted":[138],"Boltzman":[139],"Machines":[140],"(RBM)":[141],"it":[144],"RNN":[147],"solution.":[150],"validate":[152],"our":[153],"method":[154],"five":[156],"different":[157],"addition,":[160],"novel":[162],"also":[164],"result":[165],"in":[166],"better":[167],"convergence":[168],"rate":[169],"RNNs.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}