EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep learning-based holstein face recognition in real-world farming conditions

Hang Shu, Zhongming Jin, Gang Guo

Smart Agricultural Technology · 2026-03 · 13 · 101690

DOI: 10.1016/j.atech.2025.101690 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Smart Agricultural Technology, 2026-03. Verfasst von Hang Shu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Dairy Industry and Technology System, National Key Research and Development Program of China, Key Technologies Research and Development Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Non-contact biometric identification of cattle using visual facial features is now feasible due to recent advances in computer vision and deep learning. However, the lack of publicly available datasets continues to prevent the development and fair evaluation of robust models. This study attempts to address this gap by proposing Holstein2025, a benchmark dataset of individual cow face images captured using fixed-position side-view surveillance cameras in a commercial dairy farm. Holstein2025 reflects real-world environmental variability and supports both face detection and identification tasks. A systematic evaluation of state-of-the-art backbones and face recognition loss functions was conducted. The final pipeline integrates YOLO11n with an oriented bounding box head for cow face detection and alignment (average precision of 0.995, processing time of 11.2 ms), and a ConvNeXt-Tiny-based face identification network trained with an optimised ArcFace-based loss incorporating two auxiliary terms (accuracy of 0.97, processing time of 0.6 ms per face). Overall, the system runs in real time and achieved a precision of 0.98 in open set testing at a similarity threshold of 0.807. To promote reproducibility and practical application, all code and data are open-sourced and released with this paper.

Förderung

  • National Dairy Industry and Technology System
  • National Key Research and Development Program of China
  • Key Technologies Research and Development Program

Zitieren

APA

Shu, H., Jin, Z., & Guo, G. (2026). Deep learning-based holstein face recognition in real-world farming conditions. Smart Agricultural Technology, 13, 101690. https://doi.org/10.1016/j.atech.2025.101690

Vancouver

Shu H, Jin Z, Guo G. Deep learning-based holstein face recognition in real-world farming conditions. Smart Agricultural Technology. 2026;13:101690. doi:10.1016/j.atech.2025.101690

BibTeX
@article{Shu2026,
  author = {Shu, Hang and Jin, Zhongming and Guo, Gang},
  title = {Deep learning-based holstein face recognition in real-world farming conditions},
  journal = {Smart Agricultural Technology},
  year = {2026},
  volume = {13},
  pages = {101690},
  doi = {10.1016/j.atech.2025.101690}
}
Kostenlos starten →