Improved Lightweight Convolutional Networks for Classification of Grape Diseased Leaves
Aiming at the problem of low accuracy and efficiency of traditional manual detection of types of grape leaf diseases, a grape leaf disease image classification method with improved lightweight convolutional network model is proposed First, the ReLU activation function in the original network is r...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Harbin University of Science and Technology Publications
2023-06-01
|
| Series: | Journal of Harbin University of Science and Technology |
| Subjects: | |
| Online Access: | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2208 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850106336227885056 |
|---|---|
| author | HUANG Yinglai LI Ning LIU Zhenbo ZHANG Yanhua |
| author_facet | HUANG Yinglai LI Ning LIU Zhenbo ZHANG Yanhua |
| author_sort | HUANG Yinglai |
| collection | DOAJ |
| description |
Aiming at the problem of low accuracy and efficiency of traditional manual detection of types of grape leaf diseases, a grape leaf disease image classification method with improved lightweight convolutional network model is proposed First, the ReLU activation function in the original network is replaced by the ELU activation function; second, a new fully connected layer is designed, and the global average pooling layer is replaced by the global maximum pooling layer, and the output layer is improved; and then the channel attention mechanism is embedded in the network. The data is preprocessed, and divided into training and test sets in the ratio of 4 In order to simulate realistic shooting situations, methods of data enhancement are used in training to expand the data, and then the weight parameters pretrained on ImageNet are migrated to the improved model The experimental results show that the accuracy of the improved grape leaf disease classification model (Grape-Xception) improved by 2.95 percentage points to 99.57% compared to the original model, and the size of the model was 81.38 MB.Compared with other network models, the accuracy of the model is substantially improved, and it provides an accurate and efficient method for rapid diagnosis and timely prevention and control of grape leaf diseases. |
| format | Article |
| id | doaj-art-8c3cd6d4f42548a295eb761c13b197fc |
| institution | OA Journals |
| issn | 1007-2683 |
| language | zho |
| publishDate | 2023-06-01 |
| publisher | Harbin University of Science and Technology Publications |
| record_format | Article |
| series | Journal of Harbin University of Science and Technology |
| spelling | doaj-art-8c3cd6d4f42548a295eb761c13b197fc2025-08-20T02:38:51ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832023-06-0128031910.15938/j.jhust.2023.03.001Improved Lightweight Convolutional Networks for Classification of Grape Diseased LeavesHUANG Yinglai0LI Ning1LIU Zhenbo2ZHANG Yanhua3College of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, ChinaCollege of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, ChinaMaterial Science and Engineering College, Northeast Forestry University, Harbin 150040, ChinaMaterial Science and Engineering College, Northeast Forestry University, Harbin 150040, China Aiming at the problem of low accuracy and efficiency of traditional manual detection of types of grape leaf diseases, a grape leaf disease image classification method with improved lightweight convolutional network model is proposed First, the ReLU activation function in the original network is replaced by the ELU activation function; second, a new fully connected layer is designed, and the global average pooling layer is replaced by the global maximum pooling layer, and the output layer is improved; and then the channel attention mechanism is embedded in the network. The data is preprocessed, and divided into training and test sets in the ratio of 4 In order to simulate realistic shooting situations, methods of data enhancement are used in training to expand the data, and then the weight parameters pretrained on ImageNet are migrated to the improved model The experimental results show that the accuracy of the improved grape leaf disease classification model (Grape-Xception) improved by 2.95 percentage points to 99.57% compared to the original model, and the size of the model was 81.38 MB.Compared with other network models, the accuracy of the model is substantially improved, and it provides an accurate and efficient method for rapid diagnosis and timely prevention and control of grape leaf diseases.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2208grape diseaseimage classificationdeep learninglightweight convolutional networkxception |
| spellingShingle | HUANG Yinglai LI Ning LIU Zhenbo ZHANG Yanhua Improved Lightweight Convolutional Networks for Classification of Grape Diseased Leaves Journal of Harbin University of Science and Technology grape disease image classification deep learning lightweight convolutional network xception |
| title | Improved Lightweight Convolutional Networks for Classification of Grape Diseased Leaves |
| title_full | Improved Lightweight Convolutional Networks for Classification of Grape Diseased Leaves |
| title_fullStr | Improved Lightweight Convolutional Networks for Classification of Grape Diseased Leaves |
| title_full_unstemmed | Improved Lightweight Convolutional Networks for Classification of Grape Diseased Leaves |
| title_short | Improved Lightweight Convolutional Networks for Classification of Grape Diseased Leaves |
| title_sort | improved lightweight convolutional networks for classification of grape diseased leaves |
| topic | grape disease image classification deep learning lightweight convolutional network xception |
| url | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2208 |
| work_keys_str_mv | AT huangyinglai improvedlightweightconvolutionalnetworksforclassificationofgrapediseasedleaves AT lining improvedlightweightconvolutionalnetworksforclassificationofgrapediseasedleaves AT liuzhenbo improvedlightweightconvolutionalnetworksforclassificationofgrapediseasedleaves AT zhangyanhua improvedlightweightconvolutionalnetworksforclassificationofgrapediseasedleaves |