Publicación:
DEFECT CLASSIFICATION IN MELAMINE-FACED BOARDS USING MULTISPECTRAL IMAGES AND CONVOLUTIONAL NEURAL NETWORKS

Vista sencilla de ítem
dc.creatorCRISTHIAN ALEJANDRO AGUILERA CARRASCO
dc.creatorSAMUEL ELÍAS ALEJANDRO BUSTOS PUENTES
dc.date2025
dc.date.accessioned2026-03-11T15:01:28Z
dc.date.available2026-03-11T15:01:28Z
dc.date.issued2025
dc.description.abstractTHE WOOD MANUFACTURING INDUSTRY INCREASINGLY REQUIRES AUTOMATED AND INTELLIGENT SYSTEMS FOR DEFECT DETECTION TO ENSURE CONSISTENT AND RELIABLE QUALITY CONTROL. TRADITIONALLY, THIS PROCESS HAS RELIED ON VISUAL INSPECTION BY HUMAN OPERATORS, WHICH INTRODUCES VARIABILITY AND LIMITS PERFORMANCE. THIS STUDY ADDRESSES THIS CHALLENGE BY EVALUATING CONVOLUTIONAL NEURAL NETWORKS FOR AUTOMATIC DEFECT CLASSIFICATION IN MELAMINE-FACED BOARDS. MULTISPECTRAL IMAGES IN THE VISIBLE (VIS) AND NEAR-INFRARED (NIR) BANDS WERE CAPTURED UNDER REAL PRODUCTION CONDITIONS USING AN INDUSTRIAL IMAGING SYSTEM. THE RESIDUAL NETWORK 18 AND VISUAL GEOMETRY GROUP 16 MODELS WERE TESTED ON THE DATASET AND ACHIEVED ACCURACY LEVELS COMPARABLE TO THOSE OF EXPERT HUMAN INSPECTORS. THE PROPOSED METHOD CONSISTENTLY REACHED OVER 92% ACCURACY ACROSS ALL CLASSIFICATION TASKS, INDICATING ITS PRACTICAL POTENTIAL FOR INDUSTRIAL QUALITY CONTROL APPLICATIONS.
dc.formatapplication/pdf
dc.identifier.doi10.22320/s0718221x/2025.39
dc.identifier.issn0718-221X
dc.identifier.issn0717-3644
dc.identifier.urihttps://repositorio.ubiobio.cl/handle/123456789/14350
dc.language
dc.publisherMADERAS: CIENCIA Y TECNOLOGIA
dc.relation.uri10.22320/s0718221x/2025.39
dc.rightsOPEN ACCESS
dc.subjectClasificación de defectos
dc.subjectClasificación multiclase
dc.subjectImágenes multiespectrales
dc.subjectTableros melamínicos
dc.subjectRedes neuronales convolucionales
dc.subjectVisión por computador
dc.subjectDefect classification
dc.subjectMulticlass classification
dc.subjectMultispectral imaging
dc.subjectMelamine-faced board
dc.subjectConvolutional neural networks
dc.subjectComputer vision
dc.titleDEFECT CLASSIFICATION IN MELAMINE-FACED BOARDS USING MULTISPECTRAL IMAGES AND CONVOLUTIONAL NEURAL NETWORKS
dc.title.alternativeCLASIFICACIÓN DE DEFECTOS EN TABLEROS MELAMÍNICOS MEDIANTE IMÁGENES MULTIESPECTRALES Y REDES NEURONALES CONVOLUCIONALES
dc.typeARTÍCULO
dspace.entity.typePublication
oaire.licenseConditionCC BY 4.0
ubb.EstadoPUBLICADA
ubb.Otra ReparticionDEPARTAMENTO DE INGENIERIA ELECTRICA Y ELECTRONICA
ubb.Otra ReparticionDEPARTAMENTO DE INGENIERIA ELECTRICA Y ELECTRONICA
ubb.SedeCONCEPCIÓN
ubb.SedeCONCEPCIÓN
Archivos
Colecciones
Artículos científicos