{"id":"https://openalex.org/W2153316059","doi":null,"title":"FUSIONS OF CNN AND SVM CLASSIFIERS FOR RECOGNIZING HANDWRITTEN CHARACTERS","display_name":"FUSIONS OF CNN AND SVM CLASSIFIERS FOR RECOGNIZING HANDWRITTEN CHARACTERS","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2153316059","mag":"2153316059"},"language":"en","primary_location":{"id":"pmh:oai:https://spectrum.library.concordia.ca:7370","doi":null,"is_oa":true,"landing_page_url":"https://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","pdf_url":"https://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","source":{"id":"https://openalex.org/S4306400871","display_name":"Spectrum Research Repository (Concordia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I60158472","host_organization_name":"Concordia University","host_organization_lineage":["https://openalex.org/I60158472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112747213","display_name":"Xiaoxiao Niu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaoxiao Niu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5112747213"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.00019999999494757503,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/handwritten-character-recognition","display_name":"handwritten character recognition","score":0.7400000095367432},{"id":"https://openalex.org/keywords/hybrid-classifier","display_name":"hybrid classifier","score":0.5720000267028809},{"id":"https://openalex.org/keywords/classifier-combination","display_name":"classifier combination","score":0.550000011920929},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.6690000295639038},{"id":"https://openalex.org/keywords/rejection-mechanisms","display_name":"rejection mechanisms","score":0.8840000033378601},{"id":"https://openalex.org/keywords/handwritten-digit-recognition","display_name":"handwritten digit recognition","score":0.6629999876022339},{"id":"https://openalex.org/keywords/handwritten-letter-recognition","display_name":"handwritten letter recognition","score":0.8799999952316284},{"id":"https://openalex.org/keywords/english-letters","display_name":"English letters","score":0.6119999885559082},{"id":"https://openalex.org/keywords/mnist","display_name":"MNIST","score":0.7829999923706055},{"id":"https://openalex.org/keywords/handwritten-word-recognition","display_name":"handwritten word recognition","score":0.30300000309944153},{"id":"https://openalex.org/keywords/handwritten-chinese-character-recognition","display_name":"handwritten Chinese character recognition","score":0.47099998593330383}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6182358860969543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738959908485413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5540857315063477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5348618626594543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5020778179168701}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:https://spectrum.library.concordia.ca:7370","doi":null,"is_oa":true,"landing_page_url":"https://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","pdf_url":"https://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","source":{"id":"https://openalex.org/S4306400871","display_name":"Spectrum Research Repository (Concordia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I60158472","host_organization_name":"Concordia University","host_organization_lineage":["https://openalex.org/I60158472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.633.3531","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.633.3531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","raw_type":"text"},{"id":"mag:2153316059","doi":null,"is_oa":false,"landing_page_url":"https://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:https://spectrum.library.concordia.ca:7370","doi":null,"is_oa":true,"landing_page_url":"https://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","pdf_url":"https://spectrum.library.concordia.ca/7370/1/Niu_MCompSc_S2011.pdf","source":{"id":"https://openalex.org/S4306400871","display_name":"Spectrum Research Repository (Concordia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I60158472","host_organization_name":"Concordia University","host_organization_lineage":["https://openalex.org/I60158472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321588","display_name":"Concordia University","ror":"https://ror.org/0420zvk78"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2153316059.pdf","grobid_xml":"https://content.openalex.org/works/W2153316059.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W34283273","https://openalex.org/W180164409","https://openalex.org/W1503196035","https://openalex.org/W1517108682","https://openalex.org/W1574496672","https://openalex.org/W1608179252","https://openalex.org/W1821164770","https://openalex.org/W1850501806","https://openalex.org/W1881452810","https://openalex.org/W1973759055","https://openalex.org/W1985887223","https://openalex.org/W1987778768","https://openalex.org/W1997312619","https://openalex.org/W2004987553","https://openalex.org/W2010332406","https://openalex.org/W2014986661","https://openalex.org/W2024986448","https://openalex.org/W2029049225","https://openalex.org/W2035050060","https://openalex.org/W2039905248","https://openalex.org/W2042053856","https://openalex.org/W2046485094","https://openalex.org/W2048850031","https://openalex.org/W2066222526","https://openalex.org/W2083904075","https://openalex.org/W2087136607","https://openalex.org/W2092405628","https://openalex.org/W2095885101","https://openalex.org/W2107704060","https://openalex.org/W2112796928","https://openalex.org/W2115879433","https://openalex.org/W2124839441","https://openalex.org/W2124868070","https://openalex.org/W2125831352","https://openalex.org/W2126235919","https://openalex.org/W2132424367","https://openalex.org/W2134557905","https://openalex.org/W2137792864","https://openalex.org/W2139212933","https://openalex.org/W2143155961","https://openalex.org/W2149684865","https://openalex.org/W2153635508","https://openalex.org/W2156163116","https://openalex.org/W2159737176","https://openalex.org/W2164066887","https://openalex.org/W2167917621","https://openalex.org/W2169304450","https://openalex.org/W2170393096","https://openalex.org/W2171498274","https://openalex.org/W2172174689","https://openalex.org/W2303931467","https://openalex.org/W2591127855"],"related_works":["https://openalex.org/W4410154814","https://openalex.org/W4382990489","https://openalex.org/W2137664016","https://openalex.org/W4409178644","https://openalex.org/W4410857848","https://openalex.org/W7154912648","https://openalex.org/W3017078175","https://openalex.org/W2765523472","https://openalex.org/W7217532532","https://openalex.org/W4308702600"],"abstract_inverted_index":{"Off-line":[0],"handwritten":[1,54,177,180,188,269,281],"character":[2,55],"recognition":[3,15,46,56,240,252,307,332,367],"plays":[4],"an":[5],"important":[6],"role":[7],"on":[8,176,194,205,268,374],"a":[9,108,116,165,239,251,289,295,300,304],"very":[10],"large":[11],"scale":[12],"in":[13,89,182,279,292,298,319,325,359],"handwriting":[14],"systems.The":[16,57],"ultimate":[17],"goal":[18],"of":[19,51,60,68,72,93,96,164,224,236,242,254,286],"this":[20,61],"research":[21],"field":[22],"is":[23,40,63,136,149],"to":[24,36,42,64,230,250,262,370,386],"let":[25],"the":[26,45,49,70,102,120,123,129,133,146,162,170,183,187,195,206,211,217,231,266,271,312,316,322,339,345,350,362,371,375,378,381],"machine":[27],"read":[28],"generic":[29],"materials":[30],"written":[31],"by":[32,216,311],"human":[33],"beings.In":[34],"order":[35],"achieve":[37],"this,":[38],"it":[39],"necessary":[41],"further":[43],"improve":[44],"accuracy":[47],"and":[48,80,112,126,145,179,200,238,294,303,321,329,342,377],"reliability":[50,154,246,258],"current":[52],"offline":[53],"main":[58],"contribution":[59],"thesis":[62],"present":[65],"several":[66],"ways":[67],"integrating":[69],"synergy":[71],"two":[73,171],"superior":[74],"classifiers:":[75],"Convolutional":[76],"Neural":[77],"Network":[78],"(CNN)":[79],"Support":[81],"Vector":[82],"Machine":[83],"(SVM)":[84],"which":[85],"have":[86,99],"proven":[87,385],"results":[88,199,213,308],"recognizing":[90],"different":[91,284],"types":[92,285],"patterns.Two":[94],"models":[95,157,173],"new":[97],"fusions":[98],"been":[100,159],"investigated.In":[101],"hybrid":[103,219,313,351,372],"model,":[104,132],"CNN":[105,134],"works":[106,204],"as":[107,115],"trainable":[109],"feature":[110],"extractor":[111],"SVM":[113,147],"performs":[114],"recognizer.It":[117],"automatically":[118],"extracts":[119],"features":[121],"from":[122,259],"raw":[124,139],"images":[125,140],"generates":[127],"predictions.In":[128],"regular":[130],"combination":[131,363,382],"classifier":[135,148],"trained":[137,150],"with":[138,142,151,202,247],"but":[141],"normalized":[143],"sizes,":[144],"handcrafted":[152],"features.The":[153],"for":[155,315,338,344],"both":[156],"has":[158],"realized":[160],"through":[161],"introduction":[163],"rejection":[166,228,248,310,335],"mechanism.The":[167],"comparisons":[168,201],"between":[169],"proposed":[172,218],"were":[174,192,214,277,327,336],"tested":[175],"digits":[178],"letters":[181,282],"English":[184],"language,":[185],"respectively.For":[186],"digit":[189],"recognition,":[190],"experiments":[191,267],"conducted":[193],"well-known":[196],"MNIST":[197],"database.Experimental":[198],"other":[203,260,354],"same":[207],"database":[208,273],"showed":[209,348],"that":[210,349],"best":[212,264],"achieved":[215],"model:":[220],"An":[221],"error":[222,234],"rate":[223,235,241,253],"0.19%":[225],"IV":[226],"without":[227,309,334],"(compared":[229,249],"most":[232],"recent":[233],"0.35%),":[237],"94.40%":[243],"under":[244,256],"100%":[245,257],"91.51%":[255],"studies":[261],"our":[263,360],"knowledge).For":[265],"letters,":[270],"NIST":[272],"was":[274,384],"applied.Three":[275],"strategies":[276],"adopted":[278],"classifying":[280],"into":[283],"classes.They":[287],"are":[288],"26-class":[290,296,317,323],"problem":[291,297,318,324,341],"uppercases":[293,320],"lowercases,":[299],"26metaclass":[301],"problem,":[302],"52-class":[305,346],"problem.The":[306],"model":[314,352,373],"lowercases":[326],"96.2289%":[328],"90.2410%,":[330],"respectively.The":[331],"rates":[333],"92.0744%":[337],"26-metaclass":[340,376],"70.2408%":[343],"problem.Results":[347],"outperformed":[353],"single":[355],"classifiers":[356],"(SVM,":[357],"CNN)":[358],"experiments.However,":[361],"system":[364,383],"had":[365],"slight":[366],"improvements":[368],"compared":[369],"52class":[379],"problems.Besides,":[380],"be":[387],"more":[388],"reliable.":[389]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2016-06-24T00:00:00"}