{"id":"https://openalex.org/W4392344955","doi":"https://doi.org/10.1142/s0218001424520074","title":"Advancing Handwritten Musical Notation Recognition Using Deep Learning: A Convolutional Neural Network-Based Approach with Improved Accuracy","display_name":"Advancing Handwritten Musical Notation Recognition Using Deep Learning: A Convolutional Neural Network-Based Approach with Improved Accuracy","publication_year":2024,"publication_date":"2024-03-02","ids":{"openalex":"https://openalex.org/W4392344955","doi":"https://doi.org/10.1142/s0218001424520074"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001424520074","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001424520074","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5094041209","display_name":"Ee Hern Kheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134189","display_name":"Xiamen University Malaysia","ror":"https://ror.org/0331wa828","country_code":"MY","type":"education","lineage":["https://openalex.org/I191208505","https://openalex.org/I4210134189"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ee Hern Kheng","raw_affiliation_strings":["School of Electrical and Artificial Intelligence, Xiamen University Malaysia, Jalan Sunsuria, Bandar Sunsuria, 43900 Sepang, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Artificial Intelligence, Xiamen University Malaysia, Jalan Sunsuria, Bandar Sunsuria, 43900 Sepang, Selangor, Malaysia","institution_ids":["https://openalex.org/I4210134189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070852988","display_name":"Chia Pao Liew","orcid":"https://orcid.org/0000-0002-9444-1987"},"institutions":[{"id":"https://openalex.org/I4210134189","display_name":"Xiamen University Malaysia","ror":"https://ror.org/0331wa828","country_code":"MY","type":"education","lineage":["https://openalex.org/I191208505","https://openalex.org/I4210134189"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Chia Pao Liew","raw_affiliation_strings":["School of Energy and Chemical Engineering, Xiamen University Malaysia, Jalan Sunsuria, Bandar Sunsuria, 43900 Sepang, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-9444-1987","affiliations":[{"raw_affiliation_string":"School of Energy and Chemical Engineering, Xiamen University Malaysia, Jalan Sunsuria, Bandar Sunsuria, 43900 Sepang, Selangor, Malaysia","institution_ids":["https://openalex.org/I4210134189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065123431","display_name":"Tianhao Lan","orcid":"https://orcid.org/0009-0001-9459-4713"},"institutions":[{"id":"https://openalex.org/I4210134189","display_name":"Xiamen University Malaysia","ror":"https://ror.org/0331wa828","country_code":"MY","type":"education","lineage":["https://openalex.org/I191208505","https://openalex.org/I4210134189"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Tianhao Lan","raw_affiliation_strings":["School of Electrical and Artificial Intelligence, Xiamen University Malaysia, Jalan Sunsuria, Bandar Sunsuria, 43900 Sepang, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Artificial Intelligence, Xiamen University Malaysia, Jalan Sunsuria, Bandar Sunsuria, 43900 Sepang, Selangor, Malaysia","institution_ids":["https://openalex.org/I4210134189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007768740","display_name":"Kim Geok Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kim Geok Tan","raw_affiliation_strings":["Multimedia University, Faculty of Engineering and Technology, Jalan Ayer Keroh Lama, 75450 Bukit Beruang, Melaka, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia University, Faculty of Engineering and Technology, Jalan Ayer Keroh Lama, 75450 Bukit Beruang, Melaka, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070852988"],"corresponding_institution_ids":["https://openalex.org/I4210134189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01945608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"03","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9987000226974487,"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":0.9921000003814697,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7952730059623718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7901895046234131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7274858355522156},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.6727195978164673},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5951279401779175},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5642211437225342},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.516848623752594},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4828799068927765},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4661482572555542},{"id":"https://openalex.org/keywords/neocognitron","display_name":"Neocognitron","score":0.41351786255836487},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3752824664115906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35574910044670105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34756696224212646},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.20784509181976318},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.0608002245426178},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05958092212677002}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7952730059623718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901895046234131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7274858355522156},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.6727195978164673},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5951279401779175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5642211437225342},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.516848623752594},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4828799068927765},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4661482572555542},{"id":"https://openalex.org/C121144440","wikidata":"https://www.wikidata.org/wiki/Q669754","display_name":"Neocognitron","level":4,"score":0.41351786255836487},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3752824664115906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35574910044670105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34756696224212646},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.20784509181976318},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0608002245426178},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05958092212677002},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0218001424520074","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001424520074","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:shdl.mmu.edu.my:12422","is_oa":false,"landing_page_url":"http://shdl.mmu.edu.my/12422/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2800600340","https://openalex.org/W2889118961","https://openalex.org/W2917211058","https://openalex.org/W2940090474","https://openalex.org/W2968036310","https://openalex.org/W3045004532","https://openalex.org/W3080313270","https://openalex.org/W3087103930","https://openalex.org/W3091808987","https://openalex.org/W3103821002","https://openalex.org/W3171542294","https://openalex.org/W3185256938","https://openalex.org/W3214117457","https://openalex.org/W4210407519","https://openalex.org/W4231138784","https://openalex.org/W4235792399","https://openalex.org/W4239994093"],"related_works":["https://openalex.org/W2156218549","https://openalex.org/W2014970400","https://openalex.org/W1896852351","https://openalex.org/W4320485815","https://openalex.org/W4361757600","https://openalex.org/W1978173276","https://openalex.org/W2765714965","https://openalex.org/W2048023951","https://openalex.org/W1490654608","https://openalex.org/W2396258569"],"abstract_inverted_index":{"The":[0,16,70,86,111,134,158],"use":[1],"of":[2,30,47,67,100,108,140,160,199,242,256],"computers":[3],"to":[4,10,27,58,75,94,125,167],"read":[5],"musical":[6,36,53,68,84,101,207,249],"scores":[7],"is":[8,44,147,215],"referred":[9],"as":[11],"optical":[12],"music":[13],"recognition":[14,55,106,251],"(OMR).":[15],"recent":[17],"advancements":[18],"in":[19,51,60,220,260],"artificial":[20],"intelligence":[21],"and":[22,63,96,103,123,130,190,193,252],"big":[23],"data":[24,188],"have":[25],"led":[26],"the":[28,64,120,127,143,152,161,194,202,221,230,237,240,254],"development":[29],"deep":[31,78,170,257],"learning":[32,171,258],"approaches":[33,259],"for":[34,49,81,218,247],"recognizing":[35,82],"notes.":[37],"Previous":[38],"research":[39,71,225,238],"has":[40],"shown":[41],"that":[42,213],"there":[43,214],"a":[45,77,89,105,148,244],"lot":[46],"room":[48,217],"improvement":[50,150,219],"handwritten":[52,83,248],"notation":[54,250],"systems":[56],"due":[57],"differences":[59],"writing":[61],"styles":[62],"complex":[65],"structure":[66],"symbols.":[69,235],"described":[72],"here":[73],"aims":[74],"develop":[76],"learning-based":[79],"system":[80,87],"notation.":[85],"uses":[88],"convolutional":[90],"neural":[91],"network":[92,182],"(CNN)":[93],"extract":[95],"learn":[97],"pixel":[98],"features":[99],"symbols":[102,208],"achieve":[104],"accuracy":[107,139,154],"over":[109,151],"90%.":[110],"CNN":[112,135,162,195,203,245],"model":[113,136,163,196,204,246],"was":[114,164],"trained":[115],"using":[116,243],"image":[117],"samples":[118],"from":[119,155],"HOMUS":[121],"dataset":[122],"fine-tuned":[124],"minimize":[126],"loss":[128],"function":[129],"reduce":[131],"classification":[132],"errors.":[133],"achieved":[137],"an":[138],"96.95%":[141],"on":[142,228,233],"test":[144],"samples,":[145],"which":[146],"significant":[149],"86.0%":[153],"previous":[156],"studies.":[157],"performance":[159,232],"also":[165],"compared":[166],"five":[168],"state-of-the-art":[169],"methods,":[172],"namely,":[173],"quantum":[174],"gray":[175],"Wolf":[176],"optimization":[177],"(QGWO)":[178],"algorithm,":[179],"nonfully":[180],"connected":[181],"(NFC-Net)":[183],"classifier,":[184,187],"nearest":[185],"neighbor":[186],"augmentation":[189],"ensemble":[191],"learning,":[192],"outperformed":[197],"four":[198],"them.":[200],"However,":[201],"occasionally":[205],"misclassified":[206],"with":[209],"similar":[210],"shapes,":[211],"indicating":[212],"still":[216],"system\u2019s":[222],"performance.":[223],"Future":[224],"could":[226],"focus":[227],"improving":[229],"model\u2019s":[231],"similar-shaped":[234],"Overall,":[236],"demonstrates":[239],"effectiveness":[241],"highlights":[253],"potential":[255],"this":[261],"area.":[262]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}