EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparative Evaluation of YOLOv8 and YOLO11 for Image-Based Classification of Sugar Beet Seed Treatment Levels

Cihan Unal iD, Ilkay Cinar iD, Zulfi Saripinar iD, Murat Koklu iD

Sensors · 30.03.2026 · 26 (7) · 2137

DOI: 10.3390/s26072137 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Sensors, online erschienen am 30.03.2026. Verfasst von Cihan Unal und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Programming, Hacettepe University, Sincan, Ankara 06909, Türkiye. Hauptthemen laut MEDLINE: Seeds, Beta vulgaris, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific Research Projects Coordinatorship of Selçuk University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study addresses the automatic classification of sugar beet seeds according to their spraying levels using RGB images, aiming to enable a fast, practical, and non-destructive early warning system without chemical analysis. A dataset of 16,519 seed images acquired under controlled lighting conditions was used to evaluate YOLOv8-CLS and YOLO11-CLS architectures, including the n, s, m, l, and x scale variants within the Ultralytics framework. All experiments were conducted using a 10-fold cross-validation strategy, with models trained under different batch size and learning rate configurations. The results indicate that both architectures achieve reliable performance, with accuracy values ranging from approximately 78–83% for YOLOv8-CLS and 80–82% for YOLO11-CLS models. ROC-AUC scores consistently above 0.94 demonstrate strong inter-class discrimination. Misclassification analysis shows that errors mainly occur between visually similar intermediate treatment levels, particularly 25% and 50%. Despite this challenge, low log-loss values and balanced precision–recall profiles indicate stable decision behavior. Overall, the findings confirm that sugar beet seed treatment levels can be effectively distinguished using only RGB imagery, providing a potentially low-cost and scalable approach for early warning and quality control in seed treatment processes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SeedsBeta vulgarisImage Processing, Computer-AssistedClassification AlgorithmsDetection Algorithms

Stichwörter der Autor:innen

YOLO11YOLOv8deep learningimage classificationsugar beet seeds

Autor:innen und Institutionen

  • Department of Computer Programming, Hacettepe University, Sincan, Ankara 06909, Türkiye.
  • Department of Computer Engineering, Selcuk University, Selcuklu, Konya 42130, Türkiye.
  • Turkish Sugar Factories Corporation, Sugar Institute, Ankara 06810, Türkiye.

ORCID-Profile: Cihan Unal, Ilkay Cinar, Zulfi Saripinar, Murat Koklu

Förderung

  • Scientific Research Projects Coordinatorship of Selçuk University

Zitieren

APA

Unal, C., Cinar, I., Saripinar, Z., & Koklu, M. (2026). Comparative Evaluation of YOLOv8 and YOLO11 for Image-Based Classification of Sugar Beet Seed Treatment Levels. Sensors, 26(7), 2137. https://doi.org/10.3390/s26072137

Vancouver

Unal C, Cinar I, Saripinar Z, Koklu M. Comparative Evaluation of YOLOv8 and YOLO11 for Image-Based Classification of Sugar Beet Seed Treatment Levels. Sensors. 2026;26(7):2137. doi:10.3390/s26072137

BibTeX
@article{Unal2026,
  author = {Unal, Cihan and Cinar, Ilkay and Saripinar, Zulfi and Koklu, Murat},
  title = {Comparative Evaluation of YOLOv8 and YOLO11 for Image-Based Classification of Sugar Beet Seed Treatment Levels},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {2137},
  doi = {10.3390/s26072137}
}
Kostenlos starten →