{"id":"https://openalex.org/W2763468124","doi":"https://doi.org/10.1109/asar.2017.8067772","title":"Combining deep learning and language modeling for segmentation-free OCR from raw pixels","display_name":"Combining deep learning and language modeling for segmentation-free OCR from raw pixels","publication_year":2017,"publication_date":"2017-04-01","ids":{"openalex":"https://openalex.org/W2763468124","doi":"https://doi.org/10.1109/asar.2017.8067772","mag":"2763468124"},"language":"en","primary_location":{"id":"doi:10.1109/asar.2017.8067772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asar.2017.8067772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR)","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/A5046697900","display_name":"Stephen Rawls","orcid":"https://orcid.org/0000-0001-8716-2528"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Rawls","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108504544","display_name":"Huaigu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaigu Cao","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006791271","display_name":"Ekraam Sabir","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ekraam Sabir","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prem Natarajan","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.6368,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82204354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"123"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9962999820709229,"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":0.9955999851226807,"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":0.8465999960899353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7378580570220947},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5882415771484375},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.5801323056221008},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5768110752105713},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.573498547077179},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5680856704711914},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.563239336013794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5468711853027344},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5317842960357666},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.525004506111145},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4581640362739563},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.44133907556533813},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41699695587158203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41262584924697876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4112424850463867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7378580570220947},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5882415771484375},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.5801323056221008},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5768110752105713},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.573498547077179},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5680856704711914},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.563239336013794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5468711853027344},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5317842960357666},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.525004506111145},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4581640362739563},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44133907556533813},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41699695587158203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41262584924697876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4112424850463867},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asar.2017.8067772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asar.2017.8067772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W46134239","https://openalex.org/W753012316","https://openalex.org/W1026270304","https://openalex.org/W1489125746","https://openalex.org/W1522301498","https://openalex.org/W1533416326","https://openalex.org/W1685006559","https://openalex.org/W1686810756","https://openalex.org/W1815076433","https://openalex.org/W1982309299","https://openalex.org/W2004220942","https://openalex.org/W2004920872","https://openalex.org/W2017718251","https://openalex.org/W2046932483","https://openalex.org/W2050036944","https://openalex.org/W2060580591","https://openalex.org/W2063481345","https://openalex.org/W2104110038","https://openalex.org/W2109813301","https://openalex.org/W2111291958","https://openalex.org/W2124963518","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2147800946","https://openalex.org/W2170942820","https://openalex.org/W2194775991","https://openalex.org/W2950621961","https://openalex.org/W2962835968","https://openalex.org/W2963211739","https://openalex.org/W2963920996","https://openalex.org/W2964325005","https://openalex.org/W3146331408","https://openalex.org/W6622239757","https://openalex.org/W6626481562","https://openalex.org/W6629052376","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638545294","https://openalex.org/W6645763848","https://openalex.org/W6654912141","https://openalex.org/W6676558704"],"related_works":["https://openalex.org/W2790662084","https://openalex.org/W177166743","https://openalex.org/W2358941527","https://openalex.org/W2546871836","https://openalex.org/W2136485282","https://openalex.org/W4295036012","https://openalex.org/W2090093270","https://openalex.org/W2546942002","https://openalex.org/W1964805666","https://openalex.org/W2738461075"],"abstract_inverted_index":{"We":[0,15,41],"present":[1],"a":[2,17,26,37,52],"simple":[3,63],"yet":[4],"effective":[5],"LSTM-based":[6],"approach":[7],"for":[8,22],"recognizing":[9],"machine-print":[10],"text":[11],"from":[12],"raw":[13],"pixels.":[14],"use":[16,51],"fully-connected":[18],"feed-forward":[19],"neural":[20],"network":[21,44],"feature":[23],"extraction":[24],"over":[25],"sliding":[27],"window,":[28],"the":[29,43,46,72],"output":[30],"of":[31],"which":[32],"is":[33],"directly":[34],"fed":[35],"into":[36],"stacked":[38],"bi-directional":[39],"LSTM.":[40],"train":[42],"using":[45],"CTC":[47],"objective":[48],"function":[49],"and":[50],"WFST":[53],"language":[54],"model":[55],"during":[56],"recognition.":[57],"Experimental":[58],"results":[59],"show":[60],"that":[61],"this":[62],"system":[64],"outperforms":[65],"extensively":[66],"tuned":[67],"state-of-the-art":[68],"HMM":[69],"models":[70],"on":[71],"DARPA":[73],"Arabic":[74],"Machine":[75],"Print":[76],"corpus.":[77]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}