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...
Autores principales: | , , , , |
---|---|
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 |