LightMixer: A novel lightweight convolutional neural network for tomato disease detection
Tomatoes are among the very important crops grown worldwide. However, tomato diseases can harm the health of tomato plants during growth and reduce tomato yields over large areas. The development of computer vision technology offers the prospect of solving this problem. However, traditional deep lea...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1166296/full |
| _version_ | 1827951569004396544 |
|---|---|
| author | Yi Zhong Zihan Teng Mengjun Tong |
| author_facet | Yi Zhong Zihan Teng Mengjun Tong |
| author_sort | Yi Zhong |
| collection | DOAJ |
| description | Tomatoes are among the very important crops grown worldwide. However, tomato diseases can harm the health of tomato plants during growth and reduce tomato yields over large areas. The development of computer vision technology offers the prospect of solving this problem. However, traditional deep learning algorithms require a high computational cost and several parameters. Therefore, a lightweight tomato leaf disease identification model called LightMixer was designed in this study. The LightMixer model comprises a depth convolution with a Phish module and a light residual module. Depth convolution with the Phish module represents a lightweight convolution module designed to splice nonlinear activation functions with depth convolution as the backbone; it also focuses on lightweight convolutional feature extraction to facilitate deep feature fusion. The light residual module was built based on lightweight residual blocks to accelerate the computational efficiency of the entire network architecture and reduce the information loss of disease features. Experimental results show that the proposed LightMixer model achieved 99.3% accuracy on public datasets while requiring only 1.5 M parameters, an improvement over other classical convolutional neural network and lightweight models, and can be used for automatic tomato leaf disease identification on mobile devices. |
| first_indexed | 2024-04-09T13:43:40Z |
| format | Article |
| id | doaj.art-107f0518e3134c028b27551cbac25895 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-09T13:43:40Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-107f0518e3134c028b27551cbac258952023-05-09T05:41:02ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-05-011410.3389/fpls.2023.11662961166296LightMixer: A novel lightweight convolutional neural network for tomato disease detectionYi Zhong0Zihan Teng1Mengjun Tong2College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaSchool of Design, The Hong Kong Polytechnic University, Hong Kong, Hong Kong, SAR, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaTomatoes are among the very important crops grown worldwide. However, tomato diseases can harm the health of tomato plants during growth and reduce tomato yields over large areas. The development of computer vision technology offers the prospect of solving this problem. However, traditional deep learning algorithms require a high computational cost and several parameters. Therefore, a lightweight tomato leaf disease identification model called LightMixer was designed in this study. The LightMixer model comprises a depth convolution with a Phish module and a light residual module. Depth convolution with the Phish module represents a lightweight convolution module designed to splice nonlinear activation functions with depth convolution as the backbone; it also focuses on lightweight convolutional feature extraction to facilitate deep feature fusion. The light residual module was built based on lightweight residual blocks to accelerate the computational efficiency of the entire network architecture and reduce the information loss of disease features. Experimental results show that the proposed LightMixer model achieved 99.3% accuracy on public datasets while requiring only 1.5 M parameters, an improvement over other classical convolutional neural network and lightweight models, and can be used for automatic tomato leaf disease identification on mobile devices.https://www.frontiersin.org/articles/10.3389/fpls.2023.1166296/fulltomato leaf diseaselightweight modelconvolutional neural networksdeep learningdisease detection |
| spellingShingle | Yi Zhong Zihan Teng Mengjun Tong LightMixer: A novel lightweight convolutional neural network for tomato disease detection Frontiers in Plant Science tomato leaf disease lightweight model convolutional neural networks deep learning disease detection |
| title | LightMixer: A novel lightweight convolutional neural network for tomato disease detection |
| title_full | LightMixer: A novel lightweight convolutional neural network for tomato disease detection |
| title_fullStr | LightMixer: A novel lightweight convolutional neural network for tomato disease detection |
| title_full_unstemmed | LightMixer: A novel lightweight convolutional neural network for tomato disease detection |
| title_short | LightMixer: A novel lightweight convolutional neural network for tomato disease detection |
| title_sort | lightmixer a novel lightweight convolutional neural network for tomato disease detection |
| topic | tomato leaf disease lightweight model convolutional neural networks deep learning disease detection |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1166296/full |
| work_keys_str_mv | AT yizhong lightmixeranovellightweightconvolutionalneuralnetworkfortomatodiseasedetection AT zihanteng lightmixeranovellightweightconvolutionalneuralnetworkfortomatodiseasedetection AT mengjuntong lightmixeranovellightweightconvolutionalneuralnetworkfortomatodiseasedetection |