EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Non-Destructive Method for Identification of Tea Plant Cultivars Based on Deep Learning

Yi Ding, Haitao Huang, Hongchun Cui, Xinchao Wang, Yun Zhao

Forests · 03.04.2023 · 14 (4) · 728

DOI: 10.3390/f14040728 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forests, online erschienen am 03.04.2023. Verfasst von Yi Ding und 4 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Science and Technology Major Program on Agricultural New Varieties of Breeding Tea Plants, Science and Technology Innovation and Demonstration and Promotion Fund of Hangzhou Academy of Agricultural Sciences, Key Technology Research and Product Creation for the High Value Utilization of Tea in the Hangzhou Longjing Production Area.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tea plant cultivar identification is normally achieved manually or by spectroscopic, chromatographic, and other methods that are time-consuming and often inaccurate. In this paper, a method for the identification of three tea cultivars with similar leaf morphology is proposed using transfer learning by five pre-trained models: EfficientNet-B0, MobileNetV2, MobileNetV3, MobileViT-S, and ShuffleNetV2. The results showed that the best test accuracy percentages for EfficientNet-B0, MobileNetV2, MobileNetV3, MobileViT-S, and ShuffleNetV2 were 98.33, 99.67, 99.33, 98.67, and 99.00%, respectively. The most lightweight model was ShuffleNetV2, and the fastest combination was ShuffleNetV2 with 112 × 112 image resolution. Considering accuracy, the number of parameters, and floating point operations (FLOPs), MobileNetV2 was not only the most accurate model, but also both lightweight and fast. The present research could benefit both farmers and consumers via identifying tea cultivars without destructive techniques, a factor that would reduce the adulteration of commodity tea.

Förderung

  • Zhejiang Science and Technology Major Program on Agricultural New Varieties of Breeding Tea Plants
  • Science and Technology Innovation and Demonstration and Promotion Fund of Hangzhou Academy of Agricultural Sciences
  • Key Technology Research and Product Creation for the High Value Utilization of Tea in the Hangzhou Longjing Production Area
  • Key Techniques and Innovative Applications of the Inheritance and Protection of Xihu Longjing Tea

Zitieren

APA

Ding, Y., Huang, H., Cui, H., Wang, X., & Zhao, Y. (2023). A Non-Destructive Method for Identification of Tea Plant Cultivars Based on Deep Learning. Forests, 14(4), 728. https://doi.org/10.3390/f14040728

Vancouver

Ding Y, Huang H, Cui H, Wang X, Zhao Y. A Non-Destructive Method for Identification of Tea Plant Cultivars Based on Deep Learning. Forests. 2023;14(4):728. doi:10.3390/f14040728

BibTeX
@article{Ding2023,
  author = {Ding, Yi and Huang, Haitao and Cui, Hongchun and Wang, Xinchao and Zhao, Yun},
  title = {A Non-Destructive Method for Identification of Tea Plant Cultivars Based on Deep Learning},
  journal = {Forests},
  year = {2023},
  volume = {14},
  number = {4},
  pages = {728},
  doi = {10.3390/f14040728}
}
Kostenlos starten →