Convolution Self-Guided Transformer for Diagnosis and Recognition of Crop Disease in Different Environments

Accurately diagnosing crop diseases is crucial for agricultural productivity and food safety. This study addresses the challenge by developing an AI crop disease diagnosis platform, leveraging the strengths of Convolution Neural Networks (CNNs) and Vision Transformers. The proposed Convolution Self-...

Full description

Saved in:
Bibliographic Details
Main Authors: Huinian Li, Nannan Li, Wenmin Wang, Chengcheng Yang, Ningxia Chen, Fuqin Deng
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10749803/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850130157580320768
author Huinian Li
Nannan Li
Wenmin Wang
Chengcheng Yang
Ningxia Chen
Fuqin Deng
author_facet Huinian Li
Nannan Li
Wenmin Wang
Chengcheng Yang
Ningxia Chen
Fuqin Deng
author_sort Huinian Li
collection DOAJ
description Accurately diagnosing crop diseases is crucial for agricultural productivity and food safety. This study addresses the challenge by developing an AI crop disease diagnosis platform, leveraging the strengths of Convolution Neural Networks (CNNs) and Vision Transformers. The proposed Convolution Self-Guided Transformer (CSGT) model integrates CNN’s local feature extraction with the Self-Guided Transformer’s(SGT) global information processing, enhancing the precision and efficiency of agricultural diagnostics. We selected two datasets with characteristics from Jiangsu and Guangdong provinces to validate our model, respectively representing controlled and uncontrolled agricultural environments. The CSGT model demonstrates exceptional performance in diagnosing crop diseases across diverse backgrounds, overcoming the limitations of current models, especially in complex settings. The CSGT model’s CNN layer, hybrid-scale, and self-guided attention mechanisms ensure accurate diagnoses, even in the presence of background clutter. CSGT has an accuracy of 96.9%(Apple),95.8%(Corn), 96.1%(Grape), and 96.5%(Tomato) when classifying crop diseases in a stable environment, and 95.8%(Rice) when classifying diseases in a complex environment. The research results are anticipated to enhance the effectiveness and stability of natural crop disease recognition applications.
format Article
id doaj-art-b288e321d0b042be811f97da7935e32b
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-b288e321d0b042be811f97da7935e32b2025-08-20T02:32:45ZengIEEEIEEE Access2169-35362024-01-011216590316591710.1109/ACCESS.2024.349552910749803Convolution Self-Guided Transformer for Diagnosis and Recognition of Crop Disease in Different EnvironmentsHuinian Li0https://orcid.org/0000-0001-7167-0042Nannan Li1https://orcid.org/0000-0003-3688-6766Wenmin Wang2https://orcid.org/0000-0003-2664-4413Chengcheng Yang3Ningxia Chen4Fuqin Deng5https://orcid.org/0000-0001-7585-3081School of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaSchool of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaSchool of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaSchool of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, ChinaSchool of Intelligent Manufacturing, Wuyi University, Jiangmen, ChinaAccurately diagnosing crop diseases is crucial for agricultural productivity and food safety. This study addresses the challenge by developing an AI crop disease diagnosis platform, leveraging the strengths of Convolution Neural Networks (CNNs) and Vision Transformers. The proposed Convolution Self-Guided Transformer (CSGT) model integrates CNN’s local feature extraction with the Self-Guided Transformer’s(SGT) global information processing, enhancing the precision and efficiency of agricultural diagnostics. We selected two datasets with characteristics from Jiangsu and Guangdong provinces to validate our model, respectively representing controlled and uncontrolled agricultural environments. The CSGT model demonstrates exceptional performance in diagnosing crop diseases across diverse backgrounds, overcoming the limitations of current models, especially in complex settings. The CSGT model’s CNN layer, hybrid-scale, and self-guided attention mechanisms ensure accurate diagnoses, even in the presence of background clutter. CSGT has an accuracy of 96.9%(Apple),95.8%(Corn), 96.1%(Grape), and 96.5%(Tomato) when classifying crop diseases in a stable environment, and 95.8%(Rice) when classifying diseases in a complex environment. The research results are anticipated to enhance the effectiveness and stability of natural crop disease recognition applications.https://ieeexplore.ieee.org/document/10749803/Vision transformercrop protectioncrop disease diagnosisself-guided attentionAI for agriculture
spellingShingle Huinian Li
Nannan Li
Wenmin Wang
Chengcheng Yang
Ningxia Chen
Fuqin Deng
Convolution Self-Guided Transformer for Diagnosis and Recognition of Crop Disease in Different Environments
IEEE Access
Vision transformer
crop protection
crop disease diagnosis
self-guided attention
AI for agriculture
title Convolution Self-Guided Transformer for Diagnosis and Recognition of Crop Disease in Different Environments
title_full Convolution Self-Guided Transformer for Diagnosis and Recognition of Crop Disease in Different Environments
title_fullStr Convolution Self-Guided Transformer for Diagnosis and Recognition of Crop Disease in Different Environments
title_full_unstemmed Convolution Self-Guided Transformer for Diagnosis and Recognition of Crop Disease in Different Environments
title_short Convolution Self-Guided Transformer for Diagnosis and Recognition of Crop Disease in Different Environments
title_sort convolution self guided transformer for diagnosis and recognition of crop disease in different environments
topic Vision transformer
crop protection
crop disease diagnosis
self-guided attention
AI for agriculture
url https://ieeexplore.ieee.org/document/10749803/
work_keys_str_mv AT huinianli convolutionselfguidedtransformerfordiagnosisandrecognitionofcropdiseaseindifferentenvironments
AT nannanli convolutionselfguidedtransformerfordiagnosisandrecognitionofcropdiseaseindifferentenvironments
AT wenminwang convolutionselfguidedtransformerfordiagnosisandrecognitionofcropdiseaseindifferentenvironments
AT chengchengyang convolutionselfguidedtransformerfordiagnosisandrecognitionofcropdiseaseindifferentenvironments
AT ningxiachen convolutionselfguidedtransformerfordiagnosisandrecognitionofcropdiseaseindifferentenvironments
AT fuqindeng convolutionselfguidedtransformerfordiagnosisandrecognitionofcropdiseaseindifferentenvironments