EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Wheat Head Segmentation with Minimal Annotation: A Generative Approach

Jaden Myers, Keyhan Najafian iD, Farhad Maleki iD, Katie Ovens

Journal of Imaging · 21.06.2024 · 10 (7) · 152

DOI: 10.3390/jimaging10070152 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 21.06.2024. Verfasst von Jaden Myers und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada. Die Arbeit wurde bisher 8-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council, Natural Sciences and Engineering Research Council of Canada (NSERC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets. Developing such datasets is tedious and expensive. In the absence of an annotated dataset, synthetic data can be used for model development; however, due to the substantial differences between simulated and real data, a phenomenon referred to as domain gap, the resulting models often underperform when applied to real data. In this research, we aim to address this challenge by first computationally simulating a large-scale annotated dataset and then using a generative adversarial network (GAN) to fill the gap between simulated and real images. This approach results in a synthetic dataset that can be effectively utilized to train a deep-learning model. Using this approach, we developed a realistic annotated synthetic dataset for wheat head segmentation. This dataset was then used to develop a deep-learning model for semantic segmentation. The resulting model achieved a Dice score of 83.4% on an internal dataset and Dice scores of 79.6% and 83.6% on two external datasets from the Global Wheat Head Detection datasets. While we proposed this approach in the context of wheat head segmentation, it can be generalized to other crop types or, more broadly, to images with dense, repeated patterns such as those found in cellular imagery.

Schlagwörter

Stichwörter der Autor:innen

data synthesisdeep learninggenerative adversarial networkssegmentation

Autor:innen und Institutionen

  • Department of Computer Science, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada.
  • Department of Computer Science, University of Saskatchewan, Saskatoon, SK S7N 5A2, Canada.

ORCID-Profile: Keyhan Najafian, Farhad Maleki

Förderung

  • Natural Sciences and Engineering Research Council
  • Natural Sciences and Engineering Research Council of Canada (NSERC)

Zitieren

APA

Myers, J., Najafian, K., Maleki, F., & Ovens, K. (2024). Efficient Wheat Head Segmentation with Minimal Annotation: A Generative Approach. Journal of Imaging, 10(7), 152. https://doi.org/10.3390/jimaging10070152

Vancouver

Myers J, Najafian K, Maleki F, Ovens K. Efficient Wheat Head Segmentation with Minimal Annotation: A Generative Approach. Journal of Imaging. 2024;10(7):152. doi:10.3390/jimaging10070152

BibTeX
@article{Myers2024,
  author = {Myers, Jaden and Najafian, Keyhan and Maleki, Farhad and Ovens, Katie},
  title = {Efficient Wheat Head Segmentation with Minimal Annotation: A Generative Approach},
  journal = {Journal of Imaging},
  year = {2024},
  volume = {10},
  number = {7},
  pages = {152},
  doi = {10.3390/jimaging10070152}
}
Kostenlos starten →