EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Application of Deep Learning Models for the Detection of Cocoa Pods at Different Ripening Stages: An Approach with Faster R-CNN and Mask R-CNN

Juan Felipe Restrepo-Arias, María José Montoya-Castaño, María Fernanda Moreno-De La Espriella, John W. Branch-Bedoya

Computation · 02.07.2025 · 13 (7) · 159

DOI: 10.3390/computation13070159 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computation, online erschienen am 02.07.2025. Verfasst von Juan Felipe Restrepo-Arias und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad EAFIT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate classification of cocoa pod ripeness is critical for optimizing harvest timing, improving post-harvest processing, and ensuring consistent quality in chocolate production. Traditional ripeness assessment methods are often subjective, labor-intensive, or destructive, highlighting the need for automated, non-invasive solutions. This study evaluates the performance of R-CNN-based deep learning models—Faster R-CNN and Mask R-CNN—for the detection and segmentation of cocoa pods across four ripening stages (0–2 months, 2–4 months, 4–6 months, and >6 months) using the RipSetCocoaCNCH12 dataset, which is publicly accessible, comprising 4116 labeled images collected under real-world field conditions, in the context of precision agriculture. Initial experiments using pretrained weights and standard configurations on a custom COCO-format dataset yielded promising baseline results. Faster R-CNN achieved a mean average precision (mAP) of 64.15%, while Mask R-CNN reached 60.81%, with the highest per-class precision in mature pods (C4) but weaker detection in early stages (C1). To improve model robustness, the dataset was subsequently augmented and balanced, followed by targeted hyperparameter optimization for both architectures. The refined models were then benchmarked against state-of-the-art YOLOv8 networks (YOLOv8x and YOLOv8l-seg). Results showed that YOLOv8x achieved the highest mAP of 86.36%, outperforming YOLOv8l-seg (83.85%), Mask R-CNN (73.20%), and Faster R-CNN (67.75%) in overall detection accuracy. However, the R-CNN models offered valuable instance-level segmentation insights, particularly in complex backgrounds. Furthermore, a qualitative evaluation using confidence heatmaps and error analysis revealed that R-CNN architectures occasionally missed small or partially occluded pods. These findings highlight the complementary strengths of region-based and real-time detectors in precision agriculture and emphasize the need for class-specific enhancements and interpretability tools in real-world deployments.

Förderung

  • Universidad EAFIT

Zitieren

APA

Restrepo-Arias, J. F., Montoya-Castaño, M. J., Espriella, M. F. M. L., & Branch-Bedoya, J. W. (2025). An Application of Deep Learning Models for the Detection of Cocoa Pods at Different Ripening Stages: An Approach with Faster R-CNN and Mask R-CNN. Computation, 13(7), 159. https://doi.org/10.3390/computation13070159

Vancouver

Restrepo-Arias JF, Montoya-Castaño MJ, Espriella MFML, Branch-Bedoya JW. An Application of Deep Learning Models for the Detection of Cocoa Pods at Different Ripening Stages: An Approach with Faster R-CNN and Mask R-CNN. Computation. 2025;13(7):159. doi:10.3390/computation13070159

BibTeX
@article{RestrepoArias2025,
  author = {Restrepo-Arias, Juan Felipe and Montoya-Castaño, María José and Espriella, María Fernanda Moreno-De La and Branch-Bedoya, John W.},
  title = {An Application of Deep Learning Models for the Detection of Cocoa Pods at Different Ripening Stages: An Approach with Faster R-CNN and Mask R-CNN},
  journal = {Computation},
  year = {2025},
  volume = {13},
  number = {7},
  pages = {159},
  doi = {10.3390/computation13070159}
}
Kostenlos starten →