DMFGAN : a multifeature data augmentation method for grape leaf disease identification
The Plant Journal · 2024-11 · 120 (4) · 1278-1303
DOI: 10.1111/tpj.17042 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Plant Journal, online erschienen am 24.10.2024. Verfasst von Yang Hu und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha, 41004, Hunan, China. Hauptthemen laut MEDLINE: Vitis, Plant Leaves, Plant Diseases. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Scientific Research Project of Education Department of Hunan Province, Changsha Municipal Natural Science Foundation, Natural Science Foundation of Hunan Province.
Abstract (Originalsprache)
The use of deep learning techniques to identify grape leaf diseases relies on large, high‐quality datasets. However, a large number of images occupy more computing resources and are prone to pattern collapse during training. In this paper, a depth‐separable multifeature generative adversarial network (DMFGAN) was proposed to enhance grape leaf disease data. First, a multifeature extraction block (MFEB) based on the four‐channel feature fusion strategy is designed to improve the quality of the generated image and avoid the problem of poor feature learning ability of the adversarial generation network caused by the single‐channel feature extraction method. Second, a depth‐based D‐discriminator is designed to improve the discriminator capability and reduce the number of model parameters. Third, SeLU activation function was substituted for DCGAN activation function to overcome the problem that DCGAN activation function was not enough to fit grape leaf disease image data. Finally, an MFLoss function with a gradient penalty term is proposed to reduce the mode collapse during the training of generative adversarial networks. By comparing the visual indicators and evaluation indicators of the images generated by different models, and using the recognition network to verify the enhanced grape disease data, the results show that the method is effective in enhancing grape leaf disease data. Under the same experimental conditions, DMFGAN generates higher quality and more diverse images with fewer parameters than other generative adversarial networks. The mode breakdown times of generative adversarial networks in training process are reduced, which is more effective in practical application.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha, 41004, Hunan, China.
- College of Systems Engineering, National University of Defense Technology, Changsha, 410000, Hunan, China.
- Plant Protection Research Institute, Academy of Agricultural Sciences, Changsha, 410125, Hunan, China.
- Department of Soil and Water Systems, University of Idaho, Moscow, 83844, Idaho, USA.
ORCID-Profile: Guoxiong Zhou
Förderung
- Scientific Research Project of Education Department of Hunan Province
- Changsha Municipal Natural Science Foundation
- Natural Science Foundation of Hunan Province
- Hunan Key Laboratory of Intelligent Logistics Technology
Zitieren
APA
Hu, Y., Zhang, Y., Liu, S., Zhou, G., Li, M., Hu, Y., Li, J., & Sun, L. (2024). DMFGAN : a multifeature data augmentation method for grape leaf disease identification. The Plant Journal, 120(4), 1278-1303. https://doi.org/10.1111/tpj.17042
Vancouver
Hu Y, Zhang Y, Liu S, Zhou G, Li M, Hu Y, et al. DMFGAN : a multifeature data augmentation method for grape leaf disease identification. The Plant Journal. 2024;120(4):1278-1303. doi:10.1111/tpj.17042
BibTeX
@article{Hu2024,
author = {Hu, Yang and Zhang, Yukai and Liu, Shuai and Zhou, Guoxiong and Li, Mingxuan and Hu, Yahui and Li, Johnny and Sun, Lixiang},
title = {DMFGAN : a multifeature data augmentation method for grape leaf disease identification},
journal = {The Plant Journal},
year = {2024},
volume = {120},
number = {4},
pages = {1278--1303},
doi = {10.1111/tpj.17042}
}
EUVIMED