{"id":"https://openalex.org/W2157562577","doi":"https://doi.org/10.1109/icdar.2015.7333853","title":"Improving OCR for an under-resourced script using unsupervised word-spotting","display_name":"Improving OCR for an under-resourced script using unsupervised word-spotting","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2157562577","doi":"https://doi.org/10.1109/icdar.2015.7333853","mag":"2157562577"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2015.7333853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333853","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/A5001722684","display_name":"Adi Silberpfennig","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Adi Silberpfennig","raw_affiliation_strings":["The Blavatnik School of Computer Science, Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"The Blavatnik School of Computer Science, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["The Blavatnik School of Computer Science, Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"The Blavatnik School of Computer Science, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039993352","display_name":"Nachum Dershowitz","orcid":"https://orcid.org/0000-0003-0363-2735"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nachum Dershowitz","raw_affiliation_strings":["The Blavatnik School of Computer Science, Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"The Blavatnik School of Computer Science, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016931742","display_name":"Bhagesh Seraogi","orcid":"https://orcid.org/0000-0002-2831-6029"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Seraogi Bhagesh","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025093894","display_name":"B.B. Chaudhuri","orcid":"https://orcid.org/0000-0003-0297-8929"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bidyut B. Chaudhuri","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001722684"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":1.1231,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85000082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"abs 1311 4082","issue":null,"first_page":"706","last_page":"710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976999759674072,"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":0.9962000250816345,"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/spotting","display_name":"Spotting","score":0.8839306831359863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8377624750137329},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8305774927139282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6986351609230042},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.655246376991272},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.643815815448761},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.635969877243042},{"id":"https://openalex.org/keywords/intelligent-word-recognition","display_name":"Intelligent word recognition","score":0.5880117416381836},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5876902937889099},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5664572715759277},{"id":"https://openalex.org/keywords/typeface","display_name":"Typeface","score":0.5185825824737549},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.5109938383102417},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42592233419418335},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.4234510362148285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3748099207878113},{"id":"https://openalex.org/keywords/intelligent-character-recognition","display_name":"Intelligent character recognition","score":0.3178713321685791},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.26825645565986633},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.2190445065498352},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20429354906082153}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8839306831359863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377624750137329},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8305774927139282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6986351609230042},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.655246376991272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.643815815448761},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.635969877243042},{"id":"https://openalex.org/C17649283","wikidata":"https://www.wikidata.org/wiki/Q6044162","display_name":"Intelligent word recognition","level":5,"score":0.5880117416381836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5876902937889099},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5664572715759277},{"id":"https://openalex.org/C80797182","wikidata":"https://www.wikidata.org/wiki/Q17451","display_name":"Typeface","level":2,"score":0.5185825824737549},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.5109938383102417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42592233419418335},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.4234510362148285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3748099207878113},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.3178713321685791},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.26825645565986633},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.2190445065498352},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20429354906082153},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdar.2015.7333853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333853","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:10.1.1.716.283","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.716.283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tau.ac.il/%7Ewolf/papers/magicocr.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322596","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W4069827","https://openalex.org/W1521064364","https://openalex.org/W1606953891","https://openalex.org/W1646047237","https://openalex.org/W1963895093","https://openalex.org/W1980083143","https://openalex.org/W1986216697","https://openalex.org/W1990042562","https://openalex.org/W2022650584","https://openalex.org/W2062755747","https://openalex.org/W2074489476","https://openalex.org/W2087914438","https://openalex.org/W2095962836","https://openalex.org/W2100906909","https://openalex.org/W2112301665","https://openalex.org/W2114662620","https://openalex.org/W2129305389","https://openalex.org/W2141356776","https://openalex.org/W2147393756","https://openalex.org/W2161969291","https://openalex.org/W2162838084","https://openalex.org/W2163808566","https://openalex.org/W6631165897","https://openalex.org/W6636991023","https://openalex.org/W6656228717"],"related_works":["https://openalex.org/W2218402054","https://openalex.org/W4384296853","https://openalex.org/W2149231274","https://openalex.org/W4309724674","https://openalex.org/W2811459303","https://openalex.org/W2335891253","https://openalex.org/W954954433","https://openalex.org/W54024203","https://openalex.org/W2891374022","https://openalex.org/W3047617310"],"abstract_inverted_index":{"Optical":[0],"character":[1],"recognition":[2,83],"(OCR)":[3],"quality,":[4],"especially":[5],"for":[6,14,29,89],"under-resourced":[7],"scripts":[8],"like":[9],"Bangla,":[10],"as":[11,13,45],"well":[12],"documents":[15],"printed":[16],"in":[17],"old":[18],"typefaces,":[19],"is":[20,32,37,58,85,94,116,129],"a":[21,41,46,50,65,75,131],"major":[22],"concern.":[23],"An":[24],"efficient":[25,71],"and":[26],"effective":[27],"pipeline":[28],"OCR":[30,43,102,123],"betterment":[31],"proposed":[33],"here.":[34],"The":[35,100,113],"method":[36],"unsupervised.":[38],"It":[39],"employs":[40],"baseline":[42],"engine":[44,57,84],"black":[47],"box":[48],"plus":[49],"dataset":[51],"of":[52,104,119,122],"unlabeled":[53],"document":[54,77],"images.":[55],"That":[56],"applied":[59],"to":[60,69,78],"the":[61,81,98,105,117,120],"images,":[62],"followed":[63],"by":[64,126],"visual":[66],"encoding":[67],"designed":[68],"support":[70],"word":[72,92,107,114],"spotting.":[73],"Given":[74],"new":[76],"be":[79],"analyzed,":[80],"black-box":[82],"first":[86],"applied.":[87],"Then,":[88],"each":[90],"result,":[91],"spotting":[93,108],"carried":[95],"out":[96],"within":[97],"dataset.":[99],"unreliable":[101],"outputs":[103],"retrieved":[106],"results":[109],"are":[110],"then":[111],"considered.":[112],"that":[115],"centroid":[118],"set":[121],"words,":[124],"measured":[125],"edit":[127],"distance,":[128],"deemed":[130],"candidate":[132],"reading.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}