Identification of leaf diseases in field crops based on improved ShuffleNetV2
Rapid and accurate identification and timely protection of crop disease is of great importance for ensuring crop yields. Aiming at the problems of large model parameters of existing crop disease recognition methods and low recognition accuracy in the complex background of the field, we propose a lig...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-03-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2024.1342123/full |
| _version_ | 1827321095388135424 |
|---|---|
| author | Hanmi Zhou Jiageng Chen Xiaoli Niu Zhiguang Dai Long Qin Linshuang Ma Jichen Li Yumin Su Qi Wu |
| author_facet | Hanmi Zhou Jiageng Chen Xiaoli Niu Zhiguang Dai Long Qin Linshuang Ma Jichen Li Yumin Su Qi Wu |
| author_sort | Hanmi Zhou |
| collection | DOAJ |
| description | Rapid and accurate identification and timely protection of crop disease is of great importance for ensuring crop yields. Aiming at the problems of large model parameters of existing crop disease recognition methods and low recognition accuracy in the complex background of the field, we propose a lightweight crop leaf disease recognition model based on improved ShuffleNetV2. First, the repetition number and the number of output channels of the basic module of the ShuffleNetV2 model are redesigned to reduce the model parameters to make the model more lightweight while ensuring the accuracy of the model. Second, the residual structure is introduced in the basic feature extraction module to solve the gradient vanishing problem and enable the model to learn more complex feature representations. Then, parallel paths were added to the mechanism of the efficient channel attention (ECA) module, and the weights of different paths were adaptively updated by learnable parameters, and then the efficient dual channel attention (EDCA) module was proposed, which was embedded into the ShuffleNetV2 to improve the cross-channel interaction capability of the model. Finally, a multi-scale shallow feature extraction module and a multi-scale deep feature extraction module were introduced to improve the model’s ability to extract lesions at different scales. Based on the above improvements, a lightweight crop leaf disease recognition model REM-ShuffleNetV2 was proposed. Experiments results show that the accuracy and F1 score of the REM-ShuffleNetV2 model on the self-constructed field crop leaf disease dataset are 96.72% and 96.62%, which are 3.88% and 4.37% higher than that of the ShuffleNetV2 model; and the number of model parameters is 4.40M, which is 9.65% less than that of the original model. Compared with classic networks such as DenseNet121, EfficientNet, and MobileNetV3, the REM-ShuffleNetV2 model not only has higher recognition accuracy but also has fewer model parameters. The REM-ShuffleNetV2 model proposed in this study can achieve accurate identification of crop leaf disease in complex field backgrounds, and the model is small, which is convenient to deploy to the mobile end, and provides a reference for intelligent diagnosis of crop leaf disease. |
| first_indexed | 2024-04-25T01:00:25Z |
| format | Article |
| id | doaj.art-5094d604df3247f89b2e727c9ff6da06 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-25T01:00:25Z |
| publishDate | 2024-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-5094d604df3247f89b2e727c9ff6da062024-03-11T04:57:45ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-03-011510.3389/fpls.2024.13421231342123Identification of leaf diseases in field crops based on improved ShuffleNetV2Hanmi Zhou0Jiageng Chen1Xiaoli Niu2Zhiguang Dai3Long Qin4Linshuang Ma5Jichen Li6Yumin Su7Qi Wu8College of Agricultural Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Water Resource, Shenyang Agricultural University, Shenyang, ChinaRapid and accurate identification and timely protection of crop disease is of great importance for ensuring crop yields. Aiming at the problems of large model parameters of existing crop disease recognition methods and low recognition accuracy in the complex background of the field, we propose a lightweight crop leaf disease recognition model based on improved ShuffleNetV2. First, the repetition number and the number of output channels of the basic module of the ShuffleNetV2 model are redesigned to reduce the model parameters to make the model more lightweight while ensuring the accuracy of the model. Second, the residual structure is introduced in the basic feature extraction module to solve the gradient vanishing problem and enable the model to learn more complex feature representations. Then, parallel paths were added to the mechanism of the efficient channel attention (ECA) module, and the weights of different paths were adaptively updated by learnable parameters, and then the efficient dual channel attention (EDCA) module was proposed, which was embedded into the ShuffleNetV2 to improve the cross-channel interaction capability of the model. Finally, a multi-scale shallow feature extraction module and a multi-scale deep feature extraction module were introduced to improve the model’s ability to extract lesions at different scales. Based on the above improvements, a lightweight crop leaf disease recognition model REM-ShuffleNetV2 was proposed. Experiments results show that the accuracy and F1 score of the REM-ShuffleNetV2 model on the self-constructed field crop leaf disease dataset are 96.72% and 96.62%, which are 3.88% and 4.37% higher than that of the ShuffleNetV2 model; and the number of model parameters is 4.40M, which is 9.65% less than that of the original model. Compared with classic networks such as DenseNet121, EfficientNet, and MobileNetV3, the REM-ShuffleNetV2 model not only has higher recognition accuracy but also has fewer model parameters. The REM-ShuffleNetV2 model proposed in this study can achieve accurate identification of crop leaf disease in complex field backgrounds, and the model is small, which is convenient to deploy to the mobile end, and provides a reference for intelligent diagnosis of crop leaf disease.https://www.frontiersin.org/articles/10.3389/fpls.2024.1342123/fullcomplex backgroundcrop leaf diseaseShuffleNetV2EDCA moduleresidual structure |
| spellingShingle | Hanmi Zhou Jiageng Chen Xiaoli Niu Zhiguang Dai Long Qin Linshuang Ma Jichen Li Yumin Su Qi Wu Identification of leaf diseases in field crops based on improved ShuffleNetV2 Frontiers in Plant Science complex background crop leaf disease ShuffleNetV2 EDCA module residual structure |
| title | Identification of leaf diseases in field crops based on improved ShuffleNetV2 |
| title_full | Identification of leaf diseases in field crops based on improved ShuffleNetV2 |
| title_fullStr | Identification of leaf diseases in field crops based on improved ShuffleNetV2 |
| title_full_unstemmed | Identification of leaf diseases in field crops based on improved ShuffleNetV2 |
| title_short | Identification of leaf diseases in field crops based on improved ShuffleNetV2 |
| title_sort | identification of leaf diseases in field crops based on improved shufflenetv2 |
| topic | complex background crop leaf disease ShuffleNetV2 EDCA module residual structure |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2024.1342123/full |
| work_keys_str_mv | AT hanmizhou identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 AT jiagengchen identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 AT xiaoliniu identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 AT zhiguangdai identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 AT longqin identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 AT linshuangma identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 AT jichenli identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 AT yuminsu identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 AT qiwu identificationofleafdiseasesinfieldcropsbasedonimprovedshufflenetv2 |