Cargando…

FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition

Plants are widely grown around the world and have high economic benefits. plant leaf diseases not only negatively affect the healthy growth and development of plants, but also have a negative impact on the environment. While traditional manual methods of identifying plant pests and diseases are cost...

Descripción completa

Detalles Bibliográficos
Autores principales: Hu, Bo, Jiang, Wenqian, Zeng, Juan, Cheng, Chen, He, Laichang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10524271/
https://www.ncbi.nlm.nih.gov/pubmed/37771483
http://dx.doi.org/10.3389/fpls.2023.1231903
_version_ 1785110678960340992
author Hu, Bo
Jiang, Wenqian
Zeng, Juan
Cheng, Chen
He, Laichang
author_facet Hu, Bo
Jiang, Wenqian
Zeng, Juan
Cheng, Chen
He, Laichang
author_sort Hu, Bo
collection PubMed
description Plants are widely grown around the world and have high economic benefits. plant leaf diseases not only negatively affect the healthy growth and development of plants, but also have a negative impact on the environment. While traditional manual methods of identifying plant pests and diseases are costly, inefficient and inaccurate, computer vision technologies can avoid these drawbacks and also achieve shorter control times and associated cost reductions. The focusing mechanism of Transformer-based models(such as Visual Transformer) improves image interpretability and enhances the achievements of convolutional neural network (CNN) in image recognition, but Visual Transformer(ViT) performs poorly on small and medium-sized datasets. Therefore, in this paper, we propose a new hybrid architecture named FOTCA, which uses Transformer architecture based on adaptive Fourier Neural Operators(AFNO) to extract the global features in advance, and further down sampling by convolutional kernel to extract local features in a hybrid manner. To avoid the poor performance of Transformer-based architecture on small datasets, we adopt the idea of migration learning to make the model have good scientific generalization on OOD (Out-of-Distribution) samples to improve the model’s overall understanding of images. In further experiments, Focal loss and hybrid architecture can greatly improve the convergence speed and recognition accuracy of the model in ablation experiments compared with traditional models. The model proposed in this paper has the best performance with an average recognition accuracy of 99.8% and an F1-score of 0.9931. It is sufficient for deployment in plant leaf disease image recognition.
format Online
Article
Text
id pubmed-10524271
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-105242712023-09-28 FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition Hu, Bo Jiang, Wenqian Zeng, Juan Cheng, Chen He, Laichang Front Plant Sci Plant Science Plants are widely grown around the world and have high economic benefits. plant leaf diseases not only negatively affect the healthy growth and development of plants, but also have a negative impact on the environment. While traditional manual methods of identifying plant pests and diseases are costly, inefficient and inaccurate, computer vision technologies can avoid these drawbacks and also achieve shorter control times and associated cost reductions. The focusing mechanism of Transformer-based models(such as Visual Transformer) improves image interpretability and enhances the achievements of convolutional neural network (CNN) in image recognition, but Visual Transformer(ViT) performs poorly on small and medium-sized datasets. Therefore, in this paper, we propose a new hybrid architecture named FOTCA, which uses Transformer architecture based on adaptive Fourier Neural Operators(AFNO) to extract the global features in advance, and further down sampling by convolutional kernel to extract local features in a hybrid manner. To avoid the poor performance of Transformer-based architecture on small datasets, we adopt the idea of migration learning to make the model have good scientific generalization on OOD (Out-of-Distribution) samples to improve the model’s overall understanding of images. In further experiments, Focal loss and hybrid architecture can greatly improve the convergence speed and recognition accuracy of the model in ablation experiments compared with traditional models. The model proposed in this paper has the best performance with an average recognition accuracy of 99.8% and an F1-score of 0.9931. It is sufficient for deployment in plant leaf disease image recognition. Frontiers Media S.A. 2023-09-12 /pmc/articles/PMC10524271/ /pubmed/37771483 http://dx.doi.org/10.3389/fpls.2023.1231903 Text en Copyright © 2023 Hu, Jiang, Zeng, Cheng and He https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Hu, Bo
Jiang, Wenqian
Zeng, Juan
Cheng, Chen
He, Laichang
FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition
title FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition
title_full FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition
title_fullStr FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition
title_full_unstemmed FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition
title_short FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition
title_sort fotca: hybrid transformer-cnn architecture using afno for accurate plant leaf disease image recognition
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10524271/
https://www.ncbi.nlm.nih.gov/pubmed/37771483
http://dx.doi.org/10.3389/fpls.2023.1231903
work_keys_str_mv AT hubo fotcahybridtransformercnnarchitectureusingafnoforaccurateplantleafdiseaseimagerecognition
AT jiangwenqian fotcahybridtransformercnnarchitectureusingafnoforaccurateplantleafdiseaseimagerecognition
AT zengjuan fotcahybridtransformercnnarchitectureusingafnoforaccurateplantleafdiseaseimagerecognition
AT chengchen fotcahybridtransformercnnarchitectureusingafnoforaccurateplantleafdiseaseimagerecognition
AT helaichang fotcahybridtransformercnnarchitectureusingafnoforaccurateplantleafdiseaseimagerecognition