Mostrar el registro sencillo del ítem

dc.contributor.authorPourdarbani, Razieh
dc.contributor.authorSabzi, Sajad
dc.contributor.authorDehghankar, Mohsen
dc.contributor.authorRohban, Mohammad H.
dc.contributor.authorArribas Sánchez, Juan Ignacio 
dc.date.accessioned2023-12-14T09:03:41Z
dc.date.available2023-12-14T09:03:41Z
dc.date.issued2023
dc.identifier.citationAlgorithms, 2023, Vol. 16, Nº. 2, 113es
dc.identifier.issn1999-4893es
dc.identifier.urihttps://uvadoc.uva.es/handle/10324/63627
dc.descriptionProducción Científicaes
dc.description.abstractThe presence of bruises on fruits often indicates cell damage, which can lead to a decrease in the ability of the peel to keep oxygen away from the fruits, and as a result, oxygen breaks down cell walls and membranes damaging fruit content. When chemicals in the fruit are oxidized by enzymes such as polyphenol oxidase, the chemical reaction produces an undesirable and apparent brown color effect, among others. Early detection of bruising prevents low-quality fruit from entering the consumer market. Hereupon, the present paper aims at early identification of bruised lemon fruits using 3D-convolutional neural networks (3D-CNN) via a local spectral-spatial hyperspectral imaging technique, which takes into account adjacent image pixel information in both the frequency (wavelength) and spatial domains of a 3D-tensor hyperspectral image of input lemon fruits. A total of 70 sound lemons were picked up from orchards. First, all fruits were labeled and the hyperspectral images (wavelength range 400–1100 nm) were captured as belonging to the healthy (unbruised) class (class label 0). Next, bruising was applied to each lemon by freefall. Then, the hyperspectral images of all bruised samples were captured in a time gap of 8 (class label 1) and 16 h (class label 2) after bruising was induced, thus resulting in a 3-class ternary classification problem. Four well-known 3D-CNN model namely ResNet, ShuffleNet, DenseNet, and MobileNet were used to classify bruised lemons in Python. Results revealed that the highest classification accuracy (90.47%) was obtained by the ResNet model, followed by DenseNet (85.71%), ShuffleNet (80.95%) and MobileNet (73.80%); all over the test set. ResNet model had larger parameter sizes, but it was proven to be trained faster than other models with fewer number of free parameters. ShuffleNet and MobileNet were easier to train and they needed less storage, but they could not achieve a classification error as low as the other two counterparts.es
dc.format.mimetypeapplication/pdfes
dc.language.isoenges
dc.publisherMDPIes
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectFrutases
dc.subjectCítricoses
dc.subjectCítricos - Cultivoes
dc.subjectCitruses
dc.subjectCitrus cultivationes
dc.subjectCitrus fruitses
dc.subjectClassificationes
dc.subjectNeural networks (Computer science)es
dc.subjectRedes neuronales (Informática)es
dc.subjectHyperspectral imaginges
dc.subjectFruites
dc.subjectFruit - Qualityes
dc.subjectFood sciencees
dc.subjectMachine learninges
dc.subjectAprendizaje automáticoes
dc.subjectArtificial intelligencees
dc.subjectImage processing - Digital techniqueses
dc.subjectProcesamiento de imágenes - Técnicas digitales.es
dc.subjectComputer mathematics
dc.subjectOrdenadores - Matemáticas
dc.subjectNumerical analysis
dc.subjectAnálisis numérico
dc.subject.classificationBruisees
dc.titleExamination of lemon bruising using different CNN-based classifiers and local spectral-spatial hyperspectral imaginges
dc.typeinfo:eu-repo/semantics/articlees
dc.rights.holder© 2023 The authorses
dc.identifier.doi10.3390/a16020113es
dc.relation.publisherversionhttps://www.mdpi.com/1999-4893/16/2/113es
dc.identifier.publicationfirstpage113es
dc.identifier.publicationissue2es
dc.identifier.publicationtitleAlgorithmses
dc.identifier.publicationvolume16es
dc.peerreviewedSIes
dc.identifier.essn1999-4893es
dc.rightsAtribución 4.0 Internacional*
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersiones
dc.subject.unesco1203.17 Informáticaes
dc.subject.unesco1203.04 Inteligencia Artificiales
dc.subject.unesco3102 Ingeniería Agrícolaes


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem