{"id":"https://openalex.org/W6887983025","doi":"https://doi.org/10.17877/de290r-20165","title":"Segmentation-free word spotting with bag-of-features hidden Markov models","display_name":"Segmentation-free word spotting with bag-of-features hidden Markov models","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W6887983025","doi":"https://doi.org/10.17877/de290r-20165"},"language":"en","primary_location":{"id":"pmh:oai:eldorado.tu-dortmund.de:2003/38186","is_oa":true,"landing_page_url":"http://hdl.handle.net/2003/38186","pdf_url":"http://hdl.handle.net/2003/38186","source":{"id":"https://openalex.org/S4306401691","display_name":"Eldorado (Technical University of Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2003/38186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rothacker, Leonard","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rothacker, Leonard","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29034038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9146000146865845,"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":0.9146000146865845,"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":0.028599999845027924,"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":0.015599999576807022,"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/word","display_name":"Word (group theory)","score":0.633400022983551},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5873000025749207},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.572700023651123},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4706000089645386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47029998898506165},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4503999948501587},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4203999936580658},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.40849998593330383},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.39989998936653137},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3752000033855438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055999875068665},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.633400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6279000043869019},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46630001068115234},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43939998745918274},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4203999936580658},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.40849998593330383},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3752000033855438},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.33239999413490295},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C2983335612","wikidata":"https://www.wikidata.org/wiki/Q54277","display_name":"Word processing","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:eldorado.tu-dortmund.de:2003/38186","is_oa":true,"landing_page_url":"http://hdl.handle.net/2003/38186","pdf_url":"http://hdl.handle.net/2003/38186","source":{"id":"https://openalex.org/S4306401691","display_name":"Eldorado (Technical University of Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"doi:10.17877/de290r-20165","is_oa":true,"landing_page_url":"https://doi.org/10.17877/de290r-20165","pdf_url":null,"source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:eldorado.tu-dortmund.de:2003/38186","is_oa":true,"landing_page_url":"http://hdl.handle.net/2003/38186","pdf_url":"http://hdl.handle.net/2003/38186","source":{"id":"https://openalex.org/S4306401691","display_name":"Eldorado (Technical University of Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6887983025.pdf","grobid_xml":"https://content.openalex.org/works/W6887983025.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,47,160,258,360],"method":[1,221,346,361,381],"that":[2,111,134,152,187,386],"is":[3,44,50,135,141,163,174,186,198,203,234,265,273,362,378,404,412],"proposed":[4,220],"in":[5,18,33,68,95,279,305,408],"this":[6,202],"thesis":[7],"makes":[8],"document":[9,35,42,70,80,121,238,263],"images":[10,43,71,122,239,250],"searchable":[11],"with":[12,123,165,314,326,332,414],"minimum":[13],"manual":[14],"effort.":[15],"This":[16,170,233],"works":[17],"the":[19,23,30,63,92,109,129,132,138,157,178,188,192,205,208,219,228,249,270,288,296,301,321,333,345,369,380,406,409,415],"query-by-example":[20,371],"scenario":[21,372,411],"where":[22,373],"user":[24],"selects":[25],"an":[26,38,315],"exemplary":[27],"occurrence":[28],"of":[29,41,105,128,181,191,231,248,260,300,392,401],"query":[31,130,161],"word":[32,162,252,340],"a":[34,125,148,166,195,215,241,245,398],"image.":[36],"Afterwards,":[37],"entire":[39],"collection":[40,110,197],"searched":[45],"automatically.":[46,159],"major":[48],"challenge":[49],"to":[51,56,60,62,88,119,156,269,276,294,311,337,350],"detect":[52],"relevant":[53,262],"words":[54,278],"and":[55],"sort":[57],"them":[58],"according":[59,310],"similarity":[61,268,313],"query.":[64,271],"However,":[65],"recognizing":[66],"text":[67,100,193],"historic":[69,79],"can":[72,153,284,347],"be":[73,154,285,348],"considered":[74],"as":[75,240],"extremely":[76],"challenging.":[77],"Different":[78],"collections":[81],"have":[82,210,387],"highly":[83,338],"irregular":[84],"visual":[85,189,229],"appearances":[86],"due":[87],"non-standardized":[89],"layouts":[90],"or":[91,254],"large":[93],"variabilities":[94,283],"handwritten":[96],"script.":[97],"An":[98,183],"automatic":[99],"recognizer":[101],"requires":[102,222],"huge":[103],"amounts":[104],"annotated":[106,356,375,402],"samples":[107,357,403],"from":[108],"are":[112,147,308],"usually":[113],"not":[114,274],"directly":[115],"available.":[116,359],"In":[117,292,343,368],"order":[118,293],"search":[120],"just":[124],"single":[126,196],"example":[127],"word,":[131],"information":[133],"available":[136],"about":[137,227],"problem":[139],"domain":[140],"integrated":[142],"at":[143],"various":[144],"levels.":[145],"Bag-of-features":[146],"powerful":[149],"image":[150],"representation":[151],"adapted":[155],"data":[158],"represented":[164],"hidden":[167,289],"Markov":[168,290],"model.":[169,291],"statistical":[171],"sequence":[172,302,334],"model":[173,303,317,335],"very":[175],"suitable":[176],"for":[177],"sequential":[179],"structure":[180],"text.":[182,232],"important":[184],"assumption":[185],"variability":[190],"within":[194],"limited.":[199],"For":[200],"example,":[201],"typically":[204],"case":[206],"if":[207,355],"documents":[209],"been":[211,388],"written":[212],"by":[213,236,287],"only":[214,223,397],"few":[216],"writers.":[217],"Furthermore,":[218],"minimal":[224],"heuristic":[225],"assumptions":[226],"appearance":[230],"achieved":[235],"processing":[237],"whole":[242],"without":[243],"requiring":[244],"given":[246],"segmentation":[247],"on":[251,255,267,364,390],"level":[253],"line":[256],"level.":[257],"detection":[259],"potentially":[261],"regions":[264,307,325,331],"based":[266],"It":[272],"required":[275],"recognize":[277],"general.":[280],"Word":[281],"size":[282],"handled":[286],"make":[295],"computationally":[297],"costly":[298],"application":[299],"feasible":[304],"practice,":[306],"retrieved":[309],"approximate":[312,322],"efficient":[316],"decoding":[318],"algorithm.":[319],"Since":[320],"approach":[323],"retrieves":[324],"high":[327],"recall,":[328],"re-ranking":[329],"these":[330,393],"leads":[336],"accurate":[339],"spotting":[341],"results.":[342],"addition,":[344],"extended":[349],"textual":[351],"queries,":[352],"i.e.,":[353],"query-by-string,":[354],"become":[358],"evaluated":[363,389],"five":[365,394],"benchmark":[366],"datasets.":[367],"segmentation-free":[370],"no":[374],"sample":[376],"set":[377],"available,":[379,405],"outperforms":[382],"all":[383],"other":[384],"methods":[385],"any":[391],"benchmarks.":[395],"If":[396],"small":[399],"dataset":[400],"performance":[407],"query-by-string":[410],"competitive":[413],"state-of-the-art.":[416]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}