EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Maize Disease Classification System Design Based on Improved ConvNeXt

Han Li, Mingyang Qi, Baoxia Du, Qi Li, Haozhang Gao, Jun Yu, Chunguang Bi, Helong Yu, Meijing Liang, Guanshi Ye, You Tang

Sustainability · 13.10.2023 · 15 (20) · 14858

DOI: 10.3390/su152014858 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 13.10.2023. Verfasst von Han Li und 10 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Province Science nd Technology Development Program Project, Project of the Doctoral Initial Scientific Research Fund Supported by Jilin Agricultural Science and Technology University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Maize diseases have a great impact on agricultural productivity, making the classification of maize diseases a popular research area. Despite notable advancements in maize disease classification achieved via deep learning techniques, challenges such as low accuracy and identification difficulties still persist. To address these issues, this study introduced a convolutional neural network model named Sim-ConvNeXt, which incorporated a parameter-free SimAM attention module. The integration of this attention mechanism enhanced the ability of the downsample module to extract essential features of maize diseases, thereby improving classification accuracy. Moreover, transfer learning was employed to expedite model training and improve the classification performance. To evaluate the efficacy of the proposed model, a publicly accessible dataset with eight different types of maize diseases was utilized. Through the application of data augmentation techniques, including image resizing, hue, cropping, rotation, and edge padding, the dataset was expanded to comprise 17,670 images. Subsequently, a comparative analysis was conducted between the improved model and other models, wherein the approach demonstrated an accuracy rate of 95.2%. Notably, this performance represented a 1.2% enhancement over the ConvNeXt model and a 1.5% improvement over the advanced Swin Transformer model. Furthermore, the precision, recall, and F1 scores of the improved model demonstrated respective increases of 1.5% in each metric compared to the ConvNeXt model. Notably, using the Flask framework, a website for maize disease classification was developed, enabling accurate prediction of uploaded maize disease images.

Förderung

  • Jilin Province Science nd Technology Development Program Project
  • Project of the Doctoral Initial Scientific Research Fund Supported by Jilin Agricultural Science and Technology University

Zitieren

APA

Li, H., Qi, M., Du, B., Li, Q., Gao, H., Yu, J., Bi, C., Yu, H., Liang, M., Ye, G., & Tang, Y. (2023). Maize Disease Classification System Design Based on Improved ConvNeXt. Sustainability, 15(20), 14858. https://doi.org/10.3390/su152014858

Vancouver

Li H, Qi M, Du B, Li Q, Gao H, Yu J, et al. Maize Disease Classification System Design Based on Improved ConvNeXt. Sustainability. 2023;15(20):14858. doi:10.3390/su152014858

BibTeX
@article{Li2023,
  author = {Li, Han and Qi, Mingyang and Du, Baoxia and Li, Qi and Gao, Haozhang and Yu, Jun and Bi, Chunguang and Yu, Helong and Liang, Meijing and Ye, Guanshi and Tang, You},
  title = {Maize Disease Classification System Design Based on Improved ConvNeXt},
  journal = {Sustainability},
  year = {2023},
  volume = {15},
  number = {20},
  pages = {14858},
  doi = {10.3390/su152014858}
}
Kostenlos starten →