Lightweight grape leaf disease recognition method based on transformer framework

Abstract Grape disease image recognition is an important part of agricultural disease detection. Accurately identifying diseases allows for timely prevention and control at an early stage, which plays a crucial role in reducing yield losses. This study addresses the problems in grape leaf disease re...

Full description

Saved in:
Bibliographic Details
Main Authors: Ning Zhang, Enxu Zhang, Guowei Qi, Fei Li, Cheng Lv
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-13689-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763898794704896
author Ning Zhang
Enxu Zhang
Guowei Qi
Fei Li
Cheng Lv
author_facet Ning Zhang
Enxu Zhang
Guowei Qi
Fei Li
Cheng Lv
author_sort Ning Zhang
collection DOAJ
description Abstract Grape disease image recognition is an important part of agricultural disease detection. Accurately identifying diseases allows for timely prevention and control at an early stage, which plays a crucial role in reducing yield losses. This study addresses the problems in grape leaf disease recognition under small-sample conditions, such as the difficulty in capturing multi-scale features, the minuteness of features, and the weak adaptability of traditional data augmentation methods. It proposes a solution that combines a multi-scale feature hybrid fusion architecture with data augmentation. The innovation of this study lies in the following four dimensions: (1) Utilize generative models to enhance the cross-category data balancing ability under small-sample conditions and enrich the sample information in the dataset. (2) Innovatively propose the LVT Block, a multi-scale information perception hybrid module based on the Ghost and Transformer structures. This module can effectively acquire and fuse multi-scale information and global information in the feature map. (3) Use the dense connection method to combine the LVT Block and the MARI Block to propose a new architecture, the DLVT Block. By fusing multi-scale information and global information, it improves the richness of feature information. It also uses the MARI to enhance the model’s perception of disease areas and constructs an end-to-end lightweight model, DLVTNet, using the DLVT Block. Experiments show that this method achieves an average recognition rate of 98.48% on the New Plant Diseases Dataset. The number of parameters is reduced to 42.7% of that of MobileNetV4, and it maintains an accuracy of 96.12% in the tomato leaf disease test. This paper embeds pathological features into the generative adversarial process, which can effectively alleviate the problem of insufficient samples in intelligent agricultural detection. It provides a new method system with strong interpretability and excellent generalization performance for disease detection.
format Article
id doaj-art-89fa619e566044beb56b330a3d3e9dda
institution DOAJ
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-89fa619e566044beb56b330a3d3e9dda2025-08-20T03:05:17ZengNature PortfolioScientific Reports2045-23222025-08-0115112510.1038/s41598-025-13689-7Lightweight grape leaf disease recognition method based on transformer frameworkNing Zhang0Enxu Zhang1Guowei Qi2Fei Li3Cheng Lv4Engineering Research Center of Hydrogen Energy Equipment & Safety Detection, Universities of Shaanxi Province, Xijing UniversityEngineering Research Center of Hydrogen Energy Equipment & Safety Detection, Universities of Shaanxi Province, Xijing UniversityEngineering Research Center of Hydrogen Energy Equipment & Safety Detection, Universities of Shaanxi Province, Xijing UniversityEngineering Research Center of Hydrogen Energy Equipment & Safety Detection, Universities of Shaanxi Province, Xijing UniversityEngineering Research Center of Hydrogen Energy Equipment & Safety Detection, Universities of Shaanxi Province, Xijing UniversityAbstract Grape disease image recognition is an important part of agricultural disease detection. Accurately identifying diseases allows for timely prevention and control at an early stage, which plays a crucial role in reducing yield losses. This study addresses the problems in grape leaf disease recognition under small-sample conditions, such as the difficulty in capturing multi-scale features, the minuteness of features, and the weak adaptability of traditional data augmentation methods. It proposes a solution that combines a multi-scale feature hybrid fusion architecture with data augmentation. The innovation of this study lies in the following four dimensions: (1) Utilize generative models to enhance the cross-category data balancing ability under small-sample conditions and enrich the sample information in the dataset. (2) Innovatively propose the LVT Block, a multi-scale information perception hybrid module based on the Ghost and Transformer structures. This module can effectively acquire and fuse multi-scale information and global information in the feature map. (3) Use the dense connection method to combine the LVT Block and the MARI Block to propose a new architecture, the DLVT Block. By fusing multi-scale information and global information, it improves the richness of feature information. It also uses the MARI to enhance the model’s perception of disease areas and constructs an end-to-end lightweight model, DLVTNet, using the DLVT Block. Experiments show that this method achieves an average recognition rate of 98.48% on the New Plant Diseases Dataset. The number of parameters is reduced to 42.7% of that of MobileNetV4, and it maintains an accuracy of 96.12% in the tomato leaf disease test. This paper embeds pathological features into the generative adversarial process, which can effectively alleviate the problem of insufficient samples in intelligent agricultural detection. It provides a new method system with strong interpretability and excellent generalization performance for disease detection.https://doi.org/10.1038/s41598-025-13689-7Grape leaf diseaseDeep learningTransformerLightweight modelAttention mechanisms
spellingShingle Ning Zhang
Enxu Zhang
Guowei Qi
Fei Li
Cheng Lv
Lightweight grape leaf disease recognition method based on transformer framework
Scientific Reports
Grape leaf disease
Deep learning
Transformer
Lightweight model
Attention mechanisms
title Lightweight grape leaf disease recognition method based on transformer framework
title_full Lightweight grape leaf disease recognition method based on transformer framework
title_fullStr Lightweight grape leaf disease recognition method based on transformer framework
title_full_unstemmed Lightweight grape leaf disease recognition method based on transformer framework
title_short Lightweight grape leaf disease recognition method based on transformer framework
title_sort lightweight grape leaf disease recognition method based on transformer framework
topic Grape leaf disease
Deep learning
Transformer
Lightweight model
Attention mechanisms
url https://doi.org/10.1038/s41598-025-13689-7
work_keys_str_mv AT ningzhang lightweightgrapeleafdiseaserecognitionmethodbasedontransformerframework
AT enxuzhang lightweightgrapeleafdiseaserecognitionmethodbasedontransformerframework
AT guoweiqi lightweightgrapeleafdiseaserecognitionmethodbasedontransformerframework
AT feili lightweightgrapeleafdiseaserecognitionmethodbasedontransformerframework
AT chenglv lightweightgrapeleafdiseaserecognitionmethodbasedontransformerframework