{"id":"https://openalex.org/W4385470407","doi":"https://doi.org/10.1145/3604951.3605508","title":"A hybrid CNN-Transformer model for Historical Document Image Binarization","display_name":"A hybrid CNN-Transformer model for Historical Document Image Binarization","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385470407","doi":"https://doi.org/10.1145/3604951.3605508"},"language":"en","primary_location":{"id":"doi:10.1145/3604951.3605508","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604951.3605508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Historical Document Imaging and Processing","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/A5037059057","display_name":"Vahid Rezanezhad","orcid":"https://orcid.org/0009-0007-8041-6506"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Staatsbibliothek zu Berlin","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vahid Rezanezhad","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0009-0007-8041-6506","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061484718","display_name":"Konstantin Baierer","orcid":"https://orcid.org/0000-0003-2397-242X"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Staatsbibliothek zu Berlin","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Konstantin Baierer","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2397-242X","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060385793","display_name":"Clemens Neudecker","orcid":"https://orcid.org/0000-0001-5293-8322"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Staatsbibliothek zu Berlin","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Clemens Neudecker","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5293-8322","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2802918869"],"apc_list":null,"apc_paid":null,"fwci":1.0,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78197496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9901999831199646,"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":0.9857000112533569,"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":0.8043209910392761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7684339880943298},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7664514183998108},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.653445303440094},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.643257737159729},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6168805956840515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6100991368293762},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.5497685670852661},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.4851146936416626},{"id":"https://openalex.org/keywords/binary-image","display_name":"Binary image","score":0.4639183282852173},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45950740575790405},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3692724406719208},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.29045405983924866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043209910392761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7684339880943298},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7664514183998108},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.653445303440094},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.643257737159729},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6168805956840515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6100991368293762},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.5497685670852661},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.4851146936416626},{"id":"https://openalex.org/C193828747","wikidata":"https://www.wikidata.org/wiki/Q864118","display_name":"Binary image","level":4,"score":0.4639183282852173},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45950740575790405},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3692724406719208},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29045405983924866},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604951.3605508","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604951.3605508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1587119849","https://openalex.org/W2065350108","https://openalex.org/W2091863778","https://openalex.org/W2096088936","https://openalex.org/W2108598243","https://openalex.org/W2127319406","https://openalex.org/W2128060444","https://openalex.org/W2133059825","https://openalex.org/W2254039850","https://openalex.org/W2317505761","https://openalex.org/W2731900166","https://openalex.org/W2791405695","https://openalex.org/W2798943297","https://openalex.org/W2896457183","https://openalex.org/W2957223244","https://openalex.org/W2971023110","https://openalex.org/W3048313648","https://openalex.org/W3062076470","https://openalex.org/W3083907077","https://openalex.org/W3096609285","https://openalex.org/W3105826996","https://openalex.org/W3135565841","https://openalex.org/W3211950664","https://openalex.org/W4246411305","https://openalex.org/W4312263373","https://openalex.org/W4312766223"],"related_works":["https://openalex.org/W3204576215","https://openalex.org/W3160316822","https://openalex.org/W4295934125","https://openalex.org/W2022032126","https://openalex.org/W2131730163","https://openalex.org/W2051072213","https://openalex.org/W3046471831","https://openalex.org/W2784287639","https://openalex.org/W4294702218","https://openalex.org/W2119179626"],"abstract_inverted_index":{"Document":[0,107],"image":[1,12,93],"binarization":[2,40],"is":[3,41],"one":[4,64],"of":[5,39],"the":[6,44,75,99,106,113,122],"main":[7],"preprocessing":[8],"steps":[9],"in":[10,50,78],"document":[11,80,92],"analysis":[13],"for":[14,67],"text":[15,34],"recognition.":[16],"Noise,":[17],"faint":[18],"characters,":[19],"bad":[20],"scanning":[21],"conditions,":[22],"uneven":[23],"lighting":[24],"or":[25],"paper":[26],"aging":[27],"can":[28],"cause":[29],"artifacts":[30],"that":[31],"negatively":[32],"impact":[33],"recognition":[35,56],"algorithms.":[36,124],"The":[37],"task":[38],"to":[42,52,89],"segment":[43],"foreground":[45],"(text)":[46],"from":[47,72,105],"these":[48],"degradations":[49],"order":[51],"improve":[53],"optical":[54],"character":[55],"(OCR)":[57],"results.":[58],"Convolutional":[59],"Neural":[60],"Networks":[61],"(CNNs)":[62],"are":[63],"popular":[65],"method":[66],"binarization.":[68],"But":[69],"they":[70],"suffer":[71],"focusing":[73],"on":[74],"local":[76],"context":[77],"a":[79,85,91,95],"image.":[81],"We":[82],"have":[83],"applied":[84],"hybrid":[86],"CNN-Transformer":[87],"model":[88,100,120],"convert":[90],"into":[94],"binary":[96],"output.":[97],"For":[98,112],"training,":[101],"we":[102],"used":[103],"datasets":[104,114],"Image":[108],"Binarization":[109],"Contests":[110],"(DIBCO).":[111],"DIBCO-2012,":[115],"DIBCO-2017":[116],"and":[117],"DIBCO-2018,":[118],"our":[119],"outperforms":[121],"state-of-the-art":[123]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}