Simple item page
 

Convolutional Neural Network (CNN) Model for the Classification of Varieties of Date Palm Fruits (Phoenix dactylifera L.)

cris.lastimport.scopus2025-10-23T06:57:29Z
cris.virtual.author-orcid0000-0001-7223-6491
cris.virtual.author-orcid0000-0002-8011-9487
cris.virtual.author-orcid0000-0001-8487-7616
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid0000-0001-5616-5697
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid110d6c25-5395-4f20-b8e7-5e160c853b52
cris.virtualsource.author-orcid20597688-8be2-4b58-9e15-29f5ff8c53aa
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid36152344-c22b-454a-81e4-6831f3592c91
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid786b69fe-001f-4f73-9560-6e7d2061db38
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
dc.abstract.enThe popularity and demand for high-quality date palm fruits (Phoenix dactylifera L.) have been growing, and their quality largely depends on the type of handling, storage, and processing methods. The current methods of geometric evaluation and classification of date palm fruits are characterised by high labour intensity and are usually performed mechanically, which may cause additional damage and reduce the quality and value of the product. Therefore, non-contact methods are being sought based on image analysis, with digital solutions controlling the evaluation and classification processes. The main objective of this paper is to develop an automatic classification model for varieties of date palm fruits using a convolutional neural network (CNN) based on two fundamental criteria, i.e., colour difference and evaluation of geometric parameters of dates. A CNN with a fixed architecture was built, marked as DateNET, consisting of a system of five alternating Conv2D, MaxPooling2D, and Dropout classes. The validation accuracy of the model presented in this study depended on the selection of classification criteria. It was 85.24% for fruit colour-based classification and 87.62% for the geometric parameters only; however, it increased considerably to 93.41% when both the colour and geometry of dates were considered.
dc.affiliationWydział Rolnictwa, Ogrodnictwa i Biotechnologii
dc.affiliationWydział Inżynierii Środowiska i Inżynierii Mechanicznej
dc.affiliation.instituteKatedra Agronomii
dc.affiliation.instituteKatedra Genetyki i Hodowli Roślin
dc.affiliation.instituteKatedra Chemii Rolnej i Biogeochemii Åšrodowiska
dc.affiliation.instituteKatedra Inżynierii Biosystemów
dc.contributor.authorRybacki, Piotr
dc.contributor.authorNiemann, Janetta
dc.contributor.authorDerouiche, Samir
dc.contributor.authorChetehouna, Sara
dc.contributor.authorBoulaares, Islam
dc.contributor.authorSeghir, Nili Mohammed
dc.contributor.authorDiatta, Jean
dc.contributor.authorOsuch, Andrzej
dc.date.access2025-07-30
dc.date.accessioned2025-07-30T10:28:09Z
dc.date.available2025-07-30T10:28:09Z
dc.date.copyright2024-01-16
dc.date.issued2024
dc.description.abstract<jats:p>The popularity and demand for high-quality date palm fruits (Phoenix dactylifera L.) have been growing, and their quality largely depends on the type of handling, storage, and processing methods. The current methods of geometric evaluation and classification of date palm fruits are characterised by high labour intensity and are usually performed mechanically, which may cause additional damage and reduce the quality and value of the product. Therefore, non-contact methods are being sought based on image analysis, with digital solutions controlling the evaluation and classification processes. The main objective of this paper is to develop an automatic classification model for varieties of date palm fruits using a convolutional neural network (CNN) based on two fundamental criteria, i.e., colour difference and evaluation of geometric parameters of dates. A CNN with a fixed architecture was built, marked as DateNET, consisting of a system of five alternating Conv2D, MaxPooling2D, and Dropout classes. The validation accuracy of the model presented in this study depended on the selection of classification criteria. It was 85.24% for fruit colour-based classification and 87.62% for the geometric parameters only; however, it increased considerably to 93.41% when both the colour and geometry of dates were considered.</jats:p>
dc.description.accesstimeat_publication
dc.description.bibliographyil., bibliogr.
dc.description.financepublication_nocost
dc.description.financecost0,00
dc.description.if3,5
dc.description.number2
dc.description.points100
dc.description.versionfinal_published
dc.description.volume24
dc.identifier.doi10.3390/s24020558
dc.identifier.issn1424-8220
dc.identifier.urihttps://sciencerep.up.poznan.pl/handle/item/4025
dc.identifier.weblinkhttps://www.mdpi.com/1424-8220/24/2/558
dc.languageen
dc.relation.ispartofSensors
dc.relation.pagesart. 558
dc.rightsCC-BY
dc.sciencecloudsend
dc.share.typeOPEN_JOURNAL
dc.subject.endate fruits
dc.subject.enPython
dc.subject.enartificial intelligence
dc.subject.enmachine learning
dc.subject.enCNN
dc.titleConvolutional Neural Network (CNN) Model for the Classification of Varieties of Date Palm Fruits (Phoenix dactylifera L.)
dc.typeJournalArticle
dspace.entity.typePublication
oaire.citation.issue2
oaire.citation.volume24