EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Synthetic data generation for anomaly detection on table grapes

Ionut M. Motoi, Valerio Belli, Alberto Carpineto, Daniele Nardi, Thomas A. Ciarfuglia

Smart Agricultural Technology · 2025-03 · 10 · 100787

DOI: 10.1016/j.atech.2025.100787 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Smart Agricultural Technology, 2025-03. Verfasst von Ionut M. Motoi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: H2020 LEIT Information and Communication Technologies, Sapienza Università di Roma, Horizon 2020.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early detection of illnesses and pest infestations in fruit cultivation is critical for maintaining yield quality and plant health. Computer vision and robotics are increasingly employed for the automatic detection of such issues, particularly using data-driven solutions. However, the rarity of these problems makes acquiring and processing the necessary data to train such algorithms a significant obstacle. One solution to this scarcity is the generation of synthetic high-quality anomalous samples. While numerous methods exist for this task, most require highly trained individuals for setup. This work addresses the challenge of generating synthetic anomalies in an automatic fashion that requires only an initial collection of normal and anomalous samples from the user, a task that is straightforward for farmers. We demonstrate the approach in the context of table grape cultivation. Specifically, based on the observation that normal berries present relatively smooth surfaces, while defects result in more complex textures, we introduce a Dual-Canny Edge Detection (DCED) filter. This filter emphasizes the additional texture indicative of diseases, pest infestations, or other defects. Using segmentation masks provided by the Segment Anything Model, we then select and seamlessly blend anomalous berries onto normal ones. We show that the proposed dataset augmentation technique improves the accuracy of an anomaly classifier for table grapes and that the approach can be generalized to other fruit types.

Förderung

  • H2020 LEIT Information and Communication Technologies
  • Sapienza Università di Roma
  • Horizon 2020
  • MIUR
  • Horizon 2020 Framework Programme
  • European Commission

Zitieren

APA

Motoi, I. M., Belli, V., Carpineto, A., Nardi, D., & Ciarfuglia, T. A. (2025). Synthetic data generation for anomaly detection on table grapes. Smart Agricultural Technology, 10, 100787. https://doi.org/10.1016/j.atech.2025.100787

Vancouver

Motoi IM, Belli V, Carpineto A, Nardi D, Ciarfuglia TA. Synthetic data generation for anomaly detection on table grapes. Smart Agricultural Technology. 2025;10:100787. doi:10.1016/j.atech.2025.100787

BibTeX
@article{Motoi2025,
  author = {Motoi, Ionut M. and Belli, Valerio and Carpineto, Alberto and Nardi, Daniele and Ciarfuglia, Thomas A.},
  title = {Synthetic data generation for anomaly detection on table grapes},
  journal = {Smart Agricultural Technology},
  year = {2025},
  volume = {10},
  pages = {100787},
  doi = {10.1016/j.atech.2025.100787}
}
Kostenlos starten →