SalviaNet: A Machine Learning-based Leaf Signature Profiling and Species Identification of the Endemic Genus Salvia in Central Asia

Basit Öğe Kaydı
dc.authoridPalconit, Maria Gemel/0000-0002-8531-0408
dc.authoridTurdiboev, Obidjon/0000-0002-5627-9886
dc.authoridBaikova, Elena/0000-0002-7793-5344
dc.contributor.authorConcepcion, Ronnie, II
dc.contributor.authorTurdiboev, Obidjon
dc.contributor.authorHail Mendigoria, Christan
dc.contributor.authorCelep, Ferhat
dc.contributor.authorBaikova, Elena
dc.contributor.authorGemel Palconit, Maria
dc.contributor.authorRhay Vicerra, Ryan
dc.date.accessioned2025-01-21T16:33:11Z
dc.date.available2025-01-21T16:33:11Z
dc.date.issued2021
dc.departmentKırıkkale Üniversitesi
dc.descriptionIEEE Region 10 Conference (TENCON) -- DEC 07-10, 2021 -- Auckland, NEW ZEALAND
dc.description.abstractInvasive genetic and chemical-based laboratory techniques are very limited for in situ and in vivo applications especially in classifying leaf species in the wild. Out of 41 recorded Salvia species, 25 are endemic to the Central Asian region. In this study, a non-destructive model for profiling and identifying Salvia species (SalviaNet) was developed by employing computer vision allied with feature-based machine learning. The image set is composed of 25 Salvia species collected over Uzbekistan and other territories (Locus classicus) and photo-scanned to capture the totality of the leaf surface. CIELab thresholding was employed to fully segment the leaf pixels. Classification tree (CTree) was used to select the most significant spectro-textural-morphological leaf signatures resulting in only 11 attributes. These leaf signatures were profiled using the distance method with a distance power of 2. Hybrid CTree and linear discriminant analysis (CTree-LDA or SalviaNet) outperformed other computational models in classifying Salvia species based on the accuracy (90.7%) and sensitivity (90.7%). Based on profiling, leaf's red reflectance, compactness, and shape factor 2 are the strong determinants in discriminating Salvia species. Overall, the developed SalviaNet is proven reliable for on-site application and will essentially help the field of plant taxonomy.
dc.description.sponsorshipIEEE Reg 10
dc.description.sponsorshipDe La Salle University, Philippines; Uzbekistan Academy of Sciences
dc.description.sponsorshipThe authors would like to thank the following institutions for the supports they granted in this study: the De La Salle University, Philippines, and the Uzbekistan Academy of Sciences.
dc.identifier.doi10.1109/TENCON54134.2021.9707455
dc.identifier.endpage22
dc.identifier.isbn978-1-6654-9532-5
dc.identifier.scopus2-s2.0-85125964884
dc.identifier.scopusqualityQ3
dc.identifier.startpage17
dc.identifier.urihttps://doi.org/10.1109/TENCON54134.2021.9707455
dc.identifier.urihttps://hdl.handle.net/20.500.12587/23754
dc.identifier.wosWOS:000799485900004
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherIEEE
dc.relation.ispartof2021 Ieee Region 10 Conference (Tencon 2021)
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241229
dc.subjectimage processing; machine learning; Salvia; species classification; plant taxonomy
dc.titleSalviaNet: A Machine Learning-based Leaf Signature Profiling and Species Identification of the Endemic Genus Salvia in Central Asia
dc.typeConference Object

Dosyalar

Koleksiyon

WOS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu