EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Implementation of YOLOv11 for Detection and Identification of Strawberry Ripeness Stages

Nilla Mery Handayani, Yufis Azhar

Journal of Applied Informatics and Computing · 16.04.2026 · 10 (2) · 1210-1219

DOI: 10.30871/jaic.v10i2.12283 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Informatics and Computing, online erschienen am 16.04.2026. Verfasst von Nilla Mery Handayani und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents the implementation and evaluation of YOLOv11m, the latest architecture in the YOLO (You Only Look Once) object detection family, for automated multi-stage strawberry ripeness detection. The model was trained on a publicly available Strawberry-DS dataset from Mendeley Data comprising 247 annotated images across six ripeness classes: Green, White, Early-Turning, Turning, Late-Turning, and Red. The dataset was split using stratified sampling into training (70%, 172 images), validation (20%, 49 images), and test (10%, 26 images) subsets. Images were resized to 224×224 pixels and augmented using mosaic, horizontal flipping, HSV adjustment, and random scaling to improve model robustness. Training was performed for 100 epochs using SGD with cosine learning rate scheduling and early stopping. The YOLOv11m model consists of 125 fused layers, 20,034,658 parameters, and 67.7 GFLOPs. Evaluation on the validation set yielded mean precision of 0.748, recall of 0.590, mAP@0.5 of 0.654, and mAP@0.5:0.95 of 0.460. The Red (fully ripe) class achieved the highest performance (mAP@0.5 = 0.889), while transitional classes showed lower scores due to class imbalance and visual similarity. The model achieved an inference speed of 50.1 ms/image (~19 FPS) on a CPU, demonstrating real-time feasibility for industrial deployment. Unlike previous binary or three-class approaches, this study provides fine-grained six-stage ripeness detection with simultaneous object localization, offering a more granular and practically applicable framework for automated post-harvest sorting of strawberries.

Zitieren

APA

Handayani, N. M., & Azhar, Y. (2026). Implementation of YOLOv11 for Detection and Identification of Strawberry Ripeness Stages. Journal of Applied Informatics and Computing, 10(2), 1210-1219. https://doi.org/10.30871/jaic.v10i2.12283

Vancouver

Handayani NM, Azhar Y. Implementation of YOLOv11 for Detection and Identification of Strawberry Ripeness Stages. Journal of Applied Informatics and Computing. 2026;10(2):1210-1219. doi:10.30871/jaic.v10i2.12283

BibTeX
@article{Handayani2026,
  author = {Handayani, Nilla Mery and Azhar, Yufis},
  title = {Implementation of YOLOv11 for Detection and Identification of Strawberry Ripeness Stages},
  journal = {Journal of Applied Informatics and Computing},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {1210--1219},
  doi = {10.30871/jaic.v10i2.12283}
}
Kostenlos starten →