Rice pest identification based on multi-scale double-branch GAN-ResNet

Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification. Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Kui Hu [verfasserIn] YongMin Liu [verfasserIn] Jiawei Nie [verfasserIn] Xinying Zheng [verfasserIn] Wei Zhang [verfasserIn] Yuan Liu [verfasserIn] TianQiang Xie [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	smart agriculture rice diseases and insect pests deep learning image recognition ResNet data enhancement

Übergeordnetes Werk:	In: Frontiers in Plant Science - Frontiers Media S.A., 2011, 14(2023)
Übergeordnetes Werk:	volume:14 ; year:2023

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3389/fpls.2023.1167121

Katalog-ID:	DOAJ089300629

Internformat


LEADER	01000naa a22002652 4500
001	DOAJ089300629
003	DE-627
005	20230505005505.0
007	cr uuu---uuuuu
008	230505s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3389/fpls.2023.1167121 \|2 doi
035			\|a (DE-627)DOAJ089300629
035			\|a (DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a SB1-1110
100	0		\|a Kui Hu \|e verfasserin \|4 aut
245	1	0	\|a Rice pest identification based on multi-scale double-branch GAN-ResNet
264		1	\|c 2023
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification.
650		4	\|a smart agriculture
650		4	\|a rice diseases and insect pests
650		4	\|a deep learning
650		4	\|a image recognition
650		4	\|a ResNet
650		4	\|a data enhancement
653		0	\|a Plant culture
700	0		\|a Kui Hu \|e verfasserin \|4 aut
700	0		\|a YongMin Liu \|e verfasserin \|4 aut
700	0		\|a YongMin Liu \|e verfasserin \|4 aut
700	0		\|a Jiawei Nie \|e verfasserin \|4 aut
700	0		\|a Xinying Zheng \|e verfasserin \|4 aut
700	0		\|a Wei Zhang \|e verfasserin \|4 aut
700	0		\|a Wei Zhang \|e verfasserin \|4 aut
700	0		\|a Yuan Liu \|e verfasserin \|4 aut
700	0		\|a Yuan Liu \|e verfasserin \|4 aut
700	0		\|a TianQiang Xie \|e verfasserin \|4 aut
700	0		\|a TianQiang Xie \|e verfasserin \|4 aut
773	0	8	\|i In \|t Frontiers in Plant Science \|d Frontiers Media S.A., 2011 \|g 14(2023) \|w (DE-627)662359240 \|w (DE-600)2613694-6 \|x 1664462X \|7 nnns
773	1	8	\|g volume:14 \|g year:2023
856	4	0	\|u https://doi.org/10.3389/fpls.2023.1167121 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3 \|z kostenfrei
856	4	0	\|u https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/1664-462X \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_74
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2003
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 14 \|j 2023

Indexfelder

author_variant	k h kh k h kh y l yl y l yl j n jn x z xz w z wz w z wz y l yl y l yl t x tx t x tx
matchkey_str	article:1664462X:2023----::ieetdniiainaeomlicldul
hierarchy_sort_str	2023
callnumber-subject-code	SB
publishDate	2023
allfields	10.3389/fpls.2023.1167121 doi (DE-627)DOAJ089300629 (DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3 DE-627 ger DE-627 rakwb eng SB1-1110 Kui Hu verfasserin aut Rice pest identification based on multi-scale double-branch GAN-ResNet 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification. smart agriculture rice diseases and insect pests deep learning image recognition ResNet data enhancement Plant culture Kui Hu verfasserin aut YongMin Liu verfasserin aut YongMin Liu verfasserin aut Jiawei Nie verfasserin aut Xinying Zheng verfasserin aut Wei Zhang verfasserin aut Wei Zhang verfasserin aut Yuan Liu verfasserin aut Yuan Liu verfasserin aut TianQiang Xie verfasserin aut TianQiang Xie verfasserin aut In Frontiers in Plant Science Frontiers Media S.A., 2011 14(2023) (DE-627)662359240 (DE-600)2613694-6 1664462X nnns volume:14 year:2023 https://doi.org/10.3389/fpls.2023.1167121 kostenfrei https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3 kostenfrei https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full kostenfrei https://doaj.org/toc/1664-462X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 14 2023
spelling	10.3389/fpls.2023.1167121 doi (DE-627)DOAJ089300629 (DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3 DE-627 ger DE-627 rakwb eng SB1-1110 Kui Hu verfasserin aut Rice pest identification based on multi-scale double-branch GAN-ResNet 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification. smart agriculture rice diseases and insect pests deep learning image recognition ResNet data enhancement Plant culture Kui Hu verfasserin aut YongMin Liu verfasserin aut YongMin Liu verfasserin aut Jiawei Nie verfasserin aut Xinying Zheng verfasserin aut Wei Zhang verfasserin aut Wei Zhang verfasserin aut Yuan Liu verfasserin aut Yuan Liu verfasserin aut TianQiang Xie verfasserin aut TianQiang Xie verfasserin aut In Frontiers in Plant Science Frontiers Media S.A., 2011 14(2023) (DE-627)662359240 (DE-600)2613694-6 1664462X nnns volume:14 year:2023 https://doi.org/10.3389/fpls.2023.1167121 kostenfrei https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3 kostenfrei https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full kostenfrei https://doaj.org/toc/1664-462X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 14 2023
allfields_unstemmed	10.3389/fpls.2023.1167121 doi (DE-627)DOAJ089300629 (DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3 DE-627 ger DE-627 rakwb eng SB1-1110 Kui Hu verfasserin aut Rice pest identification based on multi-scale double-branch GAN-ResNet 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification. smart agriculture rice diseases and insect pests deep learning image recognition ResNet data enhancement Plant culture Kui Hu verfasserin aut YongMin Liu verfasserin aut YongMin Liu verfasserin aut Jiawei Nie verfasserin aut Xinying Zheng verfasserin aut Wei Zhang verfasserin aut Wei Zhang verfasserin aut Yuan Liu verfasserin aut Yuan Liu verfasserin aut TianQiang Xie verfasserin aut TianQiang Xie verfasserin aut In Frontiers in Plant Science Frontiers Media S.A., 2011 14(2023) (DE-627)662359240 (DE-600)2613694-6 1664462X nnns volume:14 year:2023 https://doi.org/10.3389/fpls.2023.1167121 kostenfrei https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3 kostenfrei https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full kostenfrei https://doaj.org/toc/1664-462X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 14 2023
allfieldsGer	10.3389/fpls.2023.1167121 doi (DE-627)DOAJ089300629 (DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3 DE-627 ger DE-627 rakwb eng SB1-1110 Kui Hu verfasserin aut Rice pest identification based on multi-scale double-branch GAN-ResNet 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification. smart agriculture rice diseases and insect pests deep learning image recognition ResNet data enhancement Plant culture Kui Hu verfasserin aut YongMin Liu verfasserin aut YongMin Liu verfasserin aut Jiawei Nie verfasserin aut Xinying Zheng verfasserin aut Wei Zhang verfasserin aut Wei Zhang verfasserin aut Yuan Liu verfasserin aut Yuan Liu verfasserin aut TianQiang Xie verfasserin aut TianQiang Xie verfasserin aut In Frontiers in Plant Science Frontiers Media S.A., 2011 14(2023) (DE-627)662359240 (DE-600)2613694-6 1664462X nnns volume:14 year:2023 https://doi.org/10.3389/fpls.2023.1167121 kostenfrei https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3 kostenfrei https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full kostenfrei https://doaj.org/toc/1664-462X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 14 2023
allfieldsSound	10.3389/fpls.2023.1167121 doi (DE-627)DOAJ089300629 (DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3 DE-627 ger DE-627 rakwb eng SB1-1110 Kui Hu verfasserin aut Rice pest identification based on multi-scale double-branch GAN-ResNet 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification. smart agriculture rice diseases and insect pests deep learning image recognition ResNet data enhancement Plant culture Kui Hu verfasserin aut YongMin Liu verfasserin aut YongMin Liu verfasserin aut Jiawei Nie verfasserin aut Xinying Zheng verfasserin aut Wei Zhang verfasserin aut Wei Zhang verfasserin aut Yuan Liu verfasserin aut Yuan Liu verfasserin aut TianQiang Xie verfasserin aut TianQiang Xie verfasserin aut In Frontiers in Plant Science Frontiers Media S.A., 2011 14(2023) (DE-627)662359240 (DE-600)2613694-6 1664462X nnns volume:14 year:2023 https://doi.org/10.3389/fpls.2023.1167121 kostenfrei https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3 kostenfrei https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full kostenfrei https://doaj.org/toc/1664-462X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 14 2023
language	English
source	In Frontiers in Plant Science 14(2023) volume:14 year:2023
sourceStr	In Frontiers in Plant Science 14(2023) volume:14 year:2023
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	smart agriculture rice diseases and insect pests deep learning image recognition ResNet data enhancement Plant culture
isfreeaccess_bool	true
container_title	Frontiers in Plant Science
authorswithroles_txt_mv	Kui Hu @@aut@@ YongMin Liu @@aut@@ Jiawei Nie @@aut@@ Xinying Zheng @@aut@@ Wei Zhang @@aut@@ Yuan Liu @@aut@@ TianQiang Xie @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	662359240
id	DOAJ089300629
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ089300629</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505005505.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230505s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fpls.2023.1167121</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ089300629</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">SB1-1110</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Kui Hu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Rice pest identification based on multi-scale double-branch GAN-ResNet</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">smart agriculture</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">rice diseases and insect pests</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">image recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">ResNet</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">data enhancement</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Plant culture</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Kui Hu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">YongMin Liu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">YongMin Liu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jiawei Nie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Xinying Zheng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Wei Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Wei Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Yuan Liu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Yuan Liu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">TianQiang Xie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">TianQiang Xie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Frontiers in Plant Science</subfield><subfield code="d">Frontiers Media S.A., 2011</subfield><subfield code="g">14(2023)</subfield><subfield code="w">(DE-627)662359240</subfield><subfield code="w">(DE-600)2613694-6</subfield><subfield code="x">1664462X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:14</subfield><subfield code="g">year:2023</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fpls.2023.1167121</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1664-462X</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">14</subfield><subfield code="j">2023</subfield></datafield></record></collection>
callnumber-first	S - Agriculture
author	Kui Hu
spellingShingle	Kui Hu misc SB1-1110 misc smart agriculture misc rice diseases and insect pests misc deep learning misc image recognition misc ResNet misc data enhancement misc Plant culture Rice pest identification based on multi-scale double-branch GAN-ResNet
authorStr	Kui Hu
ppnlink_with_tag_str_mv	@@773@@(DE-627)662359240
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	SB1-1110
illustrated	Not Illustrated
issn	1664462X
topic_title	SB1-1110 Rice pest identification based on multi-scale double-branch GAN-ResNet smart agriculture rice diseases and insect pests deep learning image recognition ResNet data enhancement
topic	misc SB1-1110 misc smart agriculture misc rice diseases and insect pests misc deep learning misc image recognition misc ResNet misc data enhancement misc Plant culture
topic_unstemmed	misc SB1-1110 misc smart agriculture misc rice diseases and insect pests misc deep learning misc image recognition misc ResNet misc data enhancement misc Plant culture
topic_browse	misc SB1-1110 misc smart agriculture misc rice diseases and insect pests misc deep learning misc image recognition misc ResNet misc data enhancement misc Plant culture
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Frontiers in Plant Science
hierarchy_parent_id	662359240
hierarchy_top_title	Frontiers in Plant Science
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)662359240 (DE-600)2613694-6
title	Rice pest identification based on multi-scale double-branch GAN-ResNet
ctrlnum	(DE-627)DOAJ089300629 (DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3
title_full	Rice pest identification based on multi-scale double-branch GAN-ResNet
author_sort	Kui Hu
journal	Frontiers in Plant Science
journalStr	Frontiers in Plant Science
callnumber-first-code	S
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2023
contenttype_str_mv	txt
author_browse	Kui Hu YongMin Liu Jiawei Nie Xinying Zheng Wei Zhang Yuan Liu TianQiang Xie
container_volume	14
class	SB1-1110
format_se	Elektronische Aufsätze
author-letter	Kui Hu
doi_str_mv	10.3389/fpls.2023.1167121
author2-role	verfasserin
title_sort	rice pest identification based on multi-scale double-branch gan-resnet
callnumber	SB1-1110
title_auth	Rice pest identification based on multi-scale double-branch GAN-ResNet
abstract	Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification.
abstractGer	Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification.
abstract_unstemmed	Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
title_short	Rice pest identification based on multi-scale double-branch GAN-ResNet
url	https://doi.org/10.3389/fpls.2023.1167121 https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3 https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full https://doaj.org/toc/1664-462X
remote_bool	true
author2	Kui Hu YongMin Liu Jiawei Nie Xinying Zheng Wei Zhang Yuan Liu TianQiang Xie
author2Str	Kui Hu YongMin Liu Jiawei Nie Xinying Zheng Wei Zhang Yuan Liu TianQiang Xie
ppnlink	662359240
callnumber-subject	SB - Plant Culture
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3389/fpls.2023.1167121
callnumber-a	SB1-1110
up_date	2024-07-03T22:21:21.075Z
_version_	1803598200649547776
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ089300629</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505005505.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230505s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fpls.2023.1167121</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ089300629</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ35bb1365a2844113bb13b34d12a206b3</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">SB1-1110</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Kui Hu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Rice pest identification based on multi-scale double-branch GAN-ResNet</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Rice production is crucial to the food security of all human beings, and how rice pests and diseases can be effectively prevented in and timely detected is a hotspot issue in the field of smart agriculture. Deep learning has become the preferred method for rice pest identification due to its excellent performance, especially in the aspect of autonomous learning of image features. However, in the natural environment, the dataset is too small and vulnerable to the complex background, which easily leads to problems such as overfitting, and too difficult to extract the fine features during the process of training. To solve the above problems, a Multi-Scale Dual-branch structural rice pest identification model based on a generative adversarial network and improved ResNet was proposed. Based on the ResNet model, the ConvNeXt residual block was introduced to optimize the calculation ratio of the residual blocks, and the double-branch structure was constructed to extract disease features of different sizes in the input disease images, which it adjusts the size of the convolution kernel of each branch. In the complex natural environment, data pre-processing methods such as random brightness and motion blur, and data enhancement methods such as mirroring, cropping, and scaling were used to allow the dataset of 5,932 rice disease images captured from the natural environment to be expanded to 20,000 by the dataset in this paper. The new model was trained on the new dataset to identify four common rice diseases. The experimental results showed that the recognition accuracy of the new rice pest recognition model, which was proposed for the first time, improved by 2.66% compared with the original ResNet model. Under the same experimental conditions, the new model had the best performance when compared with classical networks such as AlexNet, VGG, DenseNet, ResNet, and Transformer, and its recognition accuracy could be as high as 99.34%. The model has good generalization ability and excellent robustness, which solves the current problems in rice pest identification, such as the data set is too small and easy to lead to overfitting, and the picture background is difficult to extract disease features, and greatly improves the recognition accuracy of the model by using a multi-scale double branch structure. It provides a superior solution for crop pest and disease identification.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">smart agriculture</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">rice diseases and insect pests</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">image recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">ResNet</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">data enhancement</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Plant culture</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Kui Hu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">YongMin Liu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">YongMin Liu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jiawei Nie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Xinying Zheng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Wei Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Wei Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Yuan Liu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Yuan Liu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">TianQiang Xie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">TianQiang Xie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Frontiers in Plant Science</subfield><subfield code="d">Frontiers Media S.A., 2011</subfield><subfield code="g">14(2023)</subfield><subfield code="w">(DE-627)662359240</subfield><subfield code="w">(DE-600)2613694-6</subfield><subfield code="x">1664462X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:14</subfield><subfield code="g">year:2023</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fpls.2023.1167121</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/35bb1365a2844113bb13b34d12a206b3</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fpls.2023.1167121/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1664-462X</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">14</subfield><subfield code="j">2023</subfield></datafield></record></collection>
score	7.4007006

Nicht das Richtige dabei?

Schreiben Sie uns!

Rice pest identification based on multi-scale double-branch GAN-ResNet

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?