Publicación:
M-DETR: MULTI-SCALE DETR FOR OPTICAL MUSIC RECOGNITION

Vista sencilla de ítem
dc.creatorJOEL ALEJANDRO FUENTES LÓPEZ
dc.date2024
dc.date.accessioned2025-01-10T15:51:51Z
dc.date.available2025-01-10T15:51:51Z
dc.date.issued2024
dc.description.abstractOPTICAL MUSIC RECOGNITION (OMR) IS AN IMPORTANT WAY TO DIGITIZE SCORE IMAGES AND HAS BROAD APPLICATION PROSPECTS IN FIELDS SUCH AS THE STORAGE OF MUSIC DOCUMENTS, MUSIC EDUCATION AND DIGITAL CREATION. AS A NEW PARADIGM FOR OBJECT DETECTION, DETR (DETECTION TRANSFORMER) HAS THE ABILITY TO ASSOCIATE CONTEXTUAL INFORMATION, WHICH CAN BE EXPLOITED TO RESOLVE THE OMR TASK. HOWEVER, THE ORIGINAL DETR DOES NOT FIT OMR WELL DUE TO ITS HIGH COMPUTATIONAL COMPLEXITY AND NUMEROUS PARAMETERS. TO ADDRESS THE DETR DEFECTS AND IMPROVE THE RECOGNITION ACCURACY OF OMR, WE PROPOSE A NOVEL MULTI-SCALE DETR (M-DETR) WITH A MULTI-SCALE FEATURE FUSION MECHANISM AND IMPROVED ATTENTION MECHANISMS. FIRST, A NEW MULTI-SCALE FEATURE FUSION MECHANISM IS DESIGNED TO LET THE BACKBONE NETWORK OF M-DETR GET RICH MULTI-SCALE INFORMATION. THEN, A KEY-REGION ATTENTION MECHANISM IS INCORPORATED BASED ON THE CHARACTER THAT THE KEY INFORMATION IS CONCENTRATED ON A SCORE IMAGE. FINALLY, THE PRE-CONTEXT ATTENTION MECHANISM IS INTRODUCED TO MAKE BETTER USE OF THE CONTEXTUAL ASSOCIATION BETWEEN RECOGNITION NOTES IN MUSIC SCORES. EXPERIMENT RESULTS SHOW THAT M-DETR ACHIEVES RECOGNITION ACCURACY OF 90.6% FOR 7 TYPICAL SMALL-SIZED NOTES, WHICH IS BETTER THAN FASTER R-CNN AND YOLO V5, AND THE IMPROVEMENT RATE IS 10.02% COMPARED TO THE ORIGINAL DETR ALGORITHM. THE RESULTS INDICATE THAT M-DETR IS AN EFFECTIVE WAY FOR THE OMR TASK, WHICH ALSO PROVIDES A NEW SOLUTION FOR THE DETECTION OF SMALL-SIZED OBJECTS WITH CONTEXTUAL ASSOCIATION.
dc.formatapplication/pdf
dc.identifier.doi10.1016/j.eswa.2024.123664
dc.identifier.issn1873-6793
dc.identifier.issn0957-4174
dc.identifier.urihttps://repositorio.ubiobio.cl/handle/123456789/14007
dc.languagespa
dc.publisherEXPERT SYSTEMS WITH APPLICATIONS
dc.relation.uri10.1016/j.eswa.2024.123664
dc.rightsPUBLICADA
dc.subjectOMR
dc.subjectFeature fusion
dc.subjectDETR
dc.subjectAttention mechanism
dc.titleM-DETR: MULTI-SCALE DETR FOR OPTICAL MUSIC RECOGNITION
dc.typeARTÍCULO
dspace.entity.typePublication
ubb.EstadoPUBLICADA
ubb.Otra ReparticionDEPARTAMENTO DE CIENCIAS DE LA COMPUTACION Y TECNOLOGIA DE LA INFORMACION.
ubb.SedeCHILLÁN
Archivos
Colecciones
Artículos científicos