Cargando…
Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification
As a widely consumed fruit worldwide, it is extremely important to prevent and control disease in apple trees. In this research, we designed convolutional neural networks (CNNs) for five diseases that affect apple tree leaves based on the AlexNet model. First, the coarse-grained features of the dise...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9171387/ https://www.ncbi.nlm.nih.gov/pubmed/35685005 http://dx.doi.org/10.3389/fpls.2022.831219 |
_version_ | 1784721655656873984 |
---|---|
author | Fu, Lili Li, Shijun Sun, Yu Mu, Ye Hu, Tianli Gong, He |
author_facet | Fu, Lili Li, Shijun Sun, Yu Mu, Ye Hu, Tianli Gong, He |
author_sort | Fu, Lili |
collection | PubMed |
description | As a widely consumed fruit worldwide, it is extremely important to prevent and control disease in apple trees. In this research, we designed convolutional neural networks (CNNs) for five diseases that affect apple tree leaves based on the AlexNet model. First, the coarse-grained features of the disease are extracted in the model using dilated convolution, which helps to maintain a large receptive field while reducing the number of parameters. The parallel convolution module is added to extract leaf disease features at multiple scales. Subsequently, the series 3 × 3 convolutions shortcut connection allows the model to deal with additional nonlinearities. Further, the attention mechanism is added to all aggregated output modules to better fit channel features and reduce the impact of a complex background on the model performance. Finally, the two fully connected layers are replaced by global pooling to reduce the number of model parameters, to ensure that the features are not lost. The final recognition accuracy of the model is 97.36%, and the size of the model is 5.87 MB. In comparison with five other models, our model design is reasonable and has good robustness; further, the results show that the proposed model is lightweight and can identify apple leaf diseases with high accuracy. |
format | Online Article Text |
id | pubmed-9171387 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-91713872022-06-08 Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification Fu, Lili Li, Shijun Sun, Yu Mu, Ye Hu, Tianli Gong, He Front Plant Sci Plant Science As a widely consumed fruit worldwide, it is extremely important to prevent and control disease in apple trees. In this research, we designed convolutional neural networks (CNNs) for five diseases that affect apple tree leaves based on the AlexNet model. First, the coarse-grained features of the disease are extracted in the model using dilated convolution, which helps to maintain a large receptive field while reducing the number of parameters. The parallel convolution module is added to extract leaf disease features at multiple scales. Subsequently, the series 3 × 3 convolutions shortcut connection allows the model to deal with additional nonlinearities. Further, the attention mechanism is added to all aggregated output modules to better fit channel features and reduce the impact of a complex background on the model performance. Finally, the two fully connected layers are replaced by global pooling to reduce the number of model parameters, to ensure that the features are not lost. The final recognition accuracy of the model is 97.36%, and the size of the model is 5.87 MB. In comparison with five other models, our model design is reasonable and has good robustness; further, the results show that the proposed model is lightweight and can identify apple leaf diseases with high accuracy. Frontiers Media S.A. 2022-05-24 /pmc/articles/PMC9171387/ /pubmed/35685005 http://dx.doi.org/10.3389/fpls.2022.831219 Text en Copyright © 2022 Fu, Li, Sun, Mu, Hu and Gong. 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 Fu, Lili Li, Shijun Sun, Yu Mu, Ye Hu, Tianli Gong, He Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification |
title | Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification |
title_full | Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification |
title_fullStr | Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification |
title_full_unstemmed | Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification |
title_short | Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification |
title_sort | lightweight-convolutional neural network for apple leaf disease identification |
topic | Plant Science |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9171387/ https://www.ncbi.nlm.nih.gov/pubmed/35685005 http://dx.doi.org/10.3389/fpls.2022.831219 |
work_keys_str_mv | AT fulili lightweightconvolutionalneuralnetworkforappleleafdiseaseidentification AT lishijun lightweightconvolutionalneuralnetworkforappleleafdiseaseidentification AT sunyu lightweightconvolutionalneuralnetworkforappleleafdiseaseidentification AT muye lightweightconvolutionalneuralnetworkforappleleafdiseaseidentification AT hutianli lightweightconvolutionalneuralnetworkforappleleafdiseaseidentification AT gonghe lightweightconvolutionalneuralnetworkforappleleafdiseaseidentification |