Cargando…

Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field

The accurate classification of crop pests and diseases is essential for their prevention and control. However, datasets of pest and disease images collected in the field usually exhibit long-tailed distributions with heavy category imbalance, posing great challenges for a deep recognition and classi...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Guofeng, Chen, Guipeng, Li, Cong, Fu, Jiangfan, Guo, Yang, Liang, Hua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8287420/
https://www.ncbi.nlm.nih.gov/pubmed/34290724
http://dx.doi.org/10.3389/fpls.2021.671134
_version_ 1783723914739843072
author Yang, Guofeng
Chen, Guipeng
Li, Cong
Fu, Jiangfan
Guo, Yang
Liang, Hua
author_facet Yang, Guofeng
Chen, Guipeng
Li, Cong
Fu, Jiangfan
Guo, Yang
Liang, Hua
author_sort Yang, Guofeng
collection PubMed
description The accurate classification of crop pests and diseases is essential for their prevention and control. However, datasets of pest and disease images collected in the field usually exhibit long-tailed distributions with heavy category imbalance, posing great challenges for a deep recognition and classification model. This paper proposes a novel convolutional rebalancing network to classify rice pests and diseases from image datasets collected in the field. To improve the classification performance, the proposed network includes a convolutional rebalancing module, an image augmentation module, and a feature fusion module. In the convolutional rebalancing module, instance-balanced sampling is used to extract features of the images in the rice pest and disease dataset, while reversed sampling is used to improve feature extraction of the categories with fewer images in the dataset. Building on the convolutional rebalancing module, we design an image augmentation module to augment the training data effectively. To further enhance the classification performance, a feature fusion module fuses the image features learned by the convolutional rebalancing module and ensures that the feature extraction of the imbalanced dataset is more comprehensive. Extensive experiments in the large-scale imbalanced dataset of rice pests and diseases (18,391 images), publicly available plant image datasets (Flavia, Swedish Leaf, and UCI Leaf) and pest image datasets (SMALL and IP102) verify the robustness of the proposed network, and the results demonstrate its superior performance over state-of-the-art methods, with an accuracy of 97.58% on rice pest and disease image dataset. We conclude that the proposed network can provide an important tool for the intelligent control of rice pests and diseases in the field.
format Online
Article
Text
id pubmed-8287420
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-82874202021-07-20 Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field Yang, Guofeng Chen, Guipeng Li, Cong Fu, Jiangfan Guo, Yang Liang, Hua Front Plant Sci Plant Science The accurate classification of crop pests and diseases is essential for their prevention and control. However, datasets of pest and disease images collected in the field usually exhibit long-tailed distributions with heavy category imbalance, posing great challenges for a deep recognition and classification model. This paper proposes a novel convolutional rebalancing network to classify rice pests and diseases from image datasets collected in the field. To improve the classification performance, the proposed network includes a convolutional rebalancing module, an image augmentation module, and a feature fusion module. In the convolutional rebalancing module, instance-balanced sampling is used to extract features of the images in the rice pest and disease dataset, while reversed sampling is used to improve feature extraction of the categories with fewer images in the dataset. Building on the convolutional rebalancing module, we design an image augmentation module to augment the training data effectively. To further enhance the classification performance, a feature fusion module fuses the image features learned by the convolutional rebalancing module and ensures that the feature extraction of the imbalanced dataset is more comprehensive. Extensive experiments in the large-scale imbalanced dataset of rice pests and diseases (18,391 images), publicly available plant image datasets (Flavia, Swedish Leaf, and UCI Leaf) and pest image datasets (SMALL and IP102) verify the robustness of the proposed network, and the results demonstrate its superior performance over state-of-the-art methods, with an accuracy of 97.58% on rice pest and disease image dataset. We conclude that the proposed network can provide an important tool for the intelligent control of rice pests and diseases in the field. Frontiers Media S.A. 2021-07-05 /pmc/articles/PMC8287420/ /pubmed/34290724 http://dx.doi.org/10.3389/fpls.2021.671134 Text en Copyright © 2021 Yang, Chen, Li, Fu, Guo and Liang. 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
Yang, Guofeng
Chen, Guipeng
Li, Cong
Fu, Jiangfan
Guo, Yang
Liang, Hua
Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field
title Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field
title_full Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field
title_fullStr Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field
title_full_unstemmed Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field
title_short Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field
title_sort convolutional rebalancing network for the classification of large imbalanced rice pest and disease datasets in the field
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8287420/
https://www.ncbi.nlm.nih.gov/pubmed/34290724
http://dx.doi.org/10.3389/fpls.2021.671134
work_keys_str_mv AT yangguofeng convolutionalrebalancingnetworkfortheclassificationoflargeimbalancedricepestanddiseasedatasetsinthefield
AT chenguipeng convolutionalrebalancingnetworkfortheclassificationoflargeimbalancedricepestanddiseasedatasetsinthefield
AT licong convolutionalrebalancingnetworkfortheclassificationoflargeimbalancedricepestanddiseasedatasetsinthefield
AT fujiangfan convolutionalrebalancingnetworkfortheclassificationoflargeimbalancedricepestanddiseasedatasetsinthefield
AT guoyang convolutionalrebalancingnetworkfortheclassificationoflargeimbalancedricepestanddiseasedatasetsinthefield
AT lianghua convolutionalrebalancingnetworkfortheclassificationoflargeimbalancedricepestanddiseasedatasetsinthefield