EUVIMEDEUVIMED entdecken
Open Access

Wheat spikelet detection on RGB images using deep machine learning

M A Genaev, I D Busov, Yu V Kruchinina, V S Kova, N P Goncharov

Vavilov Journal of Genetics and Breeding · 05.03.2026 · 30 (1) · 27-35

DOI: 10.18699/vjgb-26-09 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Vavilov Journal of Genetics and Breeding, online erschienen am 05.03.2026. Verfasst von M A Genaev und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of Sciences, Novosibirsk, Russia Kurchatov Genomic Center of ICG SB …. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study addresses the challenge of automated high-throughput phenotyping of wheat spike characteristics using modern computer vision and deep learning methods. Accurate estimation of spikelet number is a key indicator of plant productivity, yet traditional manual counting approaches are labor-intensive, slow, and difficult to scale to large breeding datasets. To overcome these limitations, we propose a spikelet detection strategy based on simplified point annotations, where an expert marks only the centers of spikelets rather than drawing detailed segmentation masks or bounding boxes. This significantly reduces annotation time and lowers the overall cost of preparing training datasets for machine learning models. To determine the most effective way of utilizing such simplified annotations, three computational methods were explored: segmentation of binary masks using a U-Net architecture, density regression based on two-dimensional Gaussian distributions optimized via Kullback–Leibler divergence, and detection of fixed-size bounding regions using the YOLOv8 object detection framework. The models were evaluated on dedicated test datasets using both quantitative metrics (MAE, MAPE) and spatial localization metrics (Precision, Recall, F1 score). The results demonstrate that U-Net-based approaches provide consistently high accuracy in spikelet localization and counting while maintaining robustness to annotation imperfections. In contrast, the YOLOv8-based method showed reduced performance, likely due to the geometric mismatch between fixed-size boxes and the natural elongated shape of spikelets. Overall, the proposed methodology highlights the effectiveness of combining minimalistic point-level annotation with advanced segmentation models for automating phenotyping workflows. This approach has the potential to accelerate breeding programs, enhance the efficiency of largescale phenotypic data collection, and support further development of robust computer-vision tools for plant science applications.

Schlagwörter

Stichwörter der Autor:innen

computer visiondeep learningobject detectionphenotypingspikespikelets per spikewheat

Autor:innen und Institutionen

  • Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of Sciences, Novosibirsk, Russia Kurchatov Genomic Center of ICG SB RAS, Novosibirsk, Russia.
  • Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of Sciences, Novosibirsk, Russia Novosibirsk State University, Novosibirsk, Russia.

Zitieren

APA

Genaev, M. A., Busov, I. D., Kruchinina, Y. V., Kova, V. S., & Goncharov, N. P. (2026). Wheat spikelet detection on RGB images using deep machine learning. Vavilov Journal of Genetics and Breeding, 30(1), 27-35. https://doi.org/10.18699/vjgb-26-09

Vancouver

Genaev MA, Busov ID, Kruchinina YV, Kova VS, Goncharov NP. Wheat spikelet detection on RGB images using deep machine learning. Vavilov Journal of Genetics and Breeding. 2026;30(1):27-35. doi:10.18699/vjgb-26-09

BibTeX
@article{Genaev2026,
  author = {Genaev, M A and Busov, I D and Kruchinina, Yu V and Kova, V S and Goncharov, N P},
  title = {Wheat spikelet detection on RGB images using deep machine learning},
  journal = {Vavilov Journal of Genetics and Breeding},
  year = {2026},
  volume = {30},
  number = {1},
  pages = {27--35},
  doi = {10.18699/vjgb-26-09}
}
Kostenlos starten →