EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer

Dingju Zhu iD, Jianbin Tan, Chao Wu iD, KaiLeung Yung, Andrew W H Ip iD

Sensors · 29.06.2023 · 23 (13) · 6015

DOI: 10.3390/s23136015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.06.2023. Verfasst von Dingju Zhu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, South China Normal University, Guangzhou 510631, China. Hauptthemen laut MEDLINE: Agriculture, Fabaceae. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: “Research on teaching reform and practice based on first-class curriculum construction” of the China Society of Higher Education, “artificial intelligence” in colleges and universities in Guangdong Province, Guangdong universities (major scientific research projects—characteristic innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the development of smart agriculture, deep learning is playing an increasingly important role in crop disease recognition. The existing crop disease recognition models are mainly based on convolutional neural networks (CNN). Although traditional CNN models have excellent performance in modeling local relationships, it is difficult to extract global features. This study combines the advantages of CNN in extracting local disease information and vision transformer in obtaining global receptive fields to design a hybrid model called MSCVT. The model incorporates the multiscale self-attention module, which combines multiscale convolution and self-attention mechanisms and enables the fusion of local and global features at both the shallow and deep levels of the model. In addition, the model uses the inverted residual block to replace normal convolution to maintain a low number of parameters. To verify the validity and adaptability of MSCVT in the crop disease dataset, experiments were conducted in the PlantVillage dataset and the Apple Leaf Pathology dataset, and obtained results with recognition accuracies of 99.86% and 97.50%, respectively. In comparison with other CNN models, the proposed model achieved advanced performance in both cases. The experimental results show that MSCVT can obtain high recognition accuracy in crop disease recognition and shows excellent adaptability in multidisease recognition and small-scale disease recognition.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AgricultureFabaceaeElectric Power SuppliesNeural Networks, ComputerOrientation, Spatial

Stichwörter der Autor:innen

convolutional neural networkcrop disease recognitionimage classificationself-attention mechanismvision transformer

Autor:innen und Institutionen

  • School of Computer Science, South China Normal University, Guangzhou 510631, China.
  • School of Software, South China Normal University, Guangzhou 510631, China.
  • Department of Industrial and Systems Engineering, Hong Kong Polytechnic University, Hong Kong 999077, China.
  • Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK M4Y1M7, Canada.

ORCID-Profile: Dingju Zhu, Chao Wu, Andrew W H Ip

Förderung

  • “Research on teaching reform and practice based on first-class curriculum construction” of the China Society of Higher Education
  • “artificial intelligence” in colleges and universities in Guangdong Province
  • Guangdong universities (major scientific research projects—characteristic innovation
  • Guangdong Provincial Industry College Construction Project (Artificial Intelligence Robot Education Industry College)
  • Research on Basic and Applied Basic Research Project of Guangzhou Municipal Bureau of Science and Technology
  • Guangdong Provincial Education Department Innovation and Strengthening School Project
  • scientific research project of Guangdong Bureau of Traditional Chinese Medicine

Zitieren

APA

Zhu, D., Tan, J., Wu, C., Yung, K., & Ip, A. W. H. (2023). Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer. Sensors, 23(13), 6015. https://doi.org/10.3390/s23136015

Vancouver

Zhu D, Tan J, Wu C, Yung K, Ip AWH. Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer. Sensors. 2023;23(13):6015. doi:10.3390/s23136015

BibTeX
@article{Zhu2023,
  author = {Zhu, Dingju and Tan, Jianbin and Wu, Chao and Yung, KaiLeung and Ip, Andrew W H},
  title = {Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {13},
  pages = {6015},
  doi = {10.3390/s23136015}
}
Kostenlos starten →