Exploring Transfer Learning for Enhanced Seed Classification: Pre-trained Xception Model

Basit Öğe Kaydı
dc.authoridUNAL, Zeynep/0000-0002-9954-1151
dc.authoridReegu, Faheem/0000-0002-9167-3061
dc.authoridGulzar, Yonis/0000-0002-6515-1569
dc.authoridAyoub, Shahnawaz/0000-0002-7527-1214
dc.contributor.authorGulzar, Yonis
dc.contributor.authorUnal, Zeynep
dc.contributor.authorAyoub, Shahnawaz
dc.contributor.authorReegu, Faheem Ahmad
dc.date.accessioned2024-11-07T13:23:53Z
dc.date.available2024-11-07T13:23:53Z
dc.date.issued2024
dc.departmentNiğde Ömer Halisdemir Üniversitesi
dc.description15th International Congress on Agricultural Mechanization and Energy in Agriculture (AnkAgEng) -- OCT 29-NOV 01, 2023 -- Antalya, TURKEY
dc.description.abstractSeed classification plays a crucial role in various agricultural and industrial applications, such as crop breeding, seed quality assessment, and plant disease identification. This study presents a novel deep-learning model for seed classification. In this study, a dataset of 15 seeds has been created, containing around 3018 RGB images, with the objective of developing an accurate and efficient deep learning-based model capable of classifying seeds with high precision. In this study, we explore the effectiveness of two distinct approaches for seed classification: training the Xception model from scratch and leveraging transfer learning with the Pre-trained Xception model. The experimental results offer a comprehensive comparative analysis of training, validation, and testing outcomes. Notably, the Pre-trained Xception model showcases superior performance across various metrics. It achieves remarkable accuracy, attaining a perfect 1.0000 on both validation and test sets. Additionally, this model demonstrates significantly lower loss values throughout the training phases, highlighting its enhanced predictive capabilities. Impressively, convergence is reached with fewer epochs and in shorter training duration, further underlining the efficiency and effectiveness of the Pre-trained Xception model.
dc.description.sponsorshipAnkara Univ, Fac Agr, Dept Agr Machinery & Technologies Engn,Springer Nature,Turk Traktor,Ziraat Bankasi,European Soc Agr Engineers,Amer Soc Agr & Biol Engineers,Int Commiss Agr & Biosystems Engn
dc.description.sponsorshipDeanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia [GRANT5,362]
dc.description.sponsorshipThis work was supported by the Deanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia, under Project GRANT5,362.
dc.identifier.doi10.1007/978-3-031-51579-8_14
dc.identifier.endpage147
dc.identifier.isbn978-3-031-51581-1
dc.identifier.isbn978-3-031-51579-8
dc.identifier.isbn978-3-031-51578-1
dc.identifier.issn2366-2557
dc.identifier.issn2366-2565
dc.identifier.scopus2-s2.0-85184806638
dc.identifier.scopusqualityQ4
dc.identifier.startpage137
dc.identifier.urihttps://doi.org/10.1007/978-3-031-51579-8_14
dc.identifier.urihttps://hdl.handle.net/11480/13766
dc.identifier.volume458
dc.identifier.wosWOS:001265095100014
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSpringer International Publishing Ag
dc.relation.ispartof15th International Congress on Agricultural Mechanization and Energy in Agriculture, Ankageng 2023
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241106
dc.subjectSeed Classification
dc.subjectDeep Learning
dc.subjectCNN
dc.titleExploring Transfer Learning for Enhanced Seed Classification: Pre-trained Xception Model
dc.typeConference Object

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu