GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases
Most convolutional neural network (CNN) models have various difficulties in identifying crop diseases owing to morphological and physiological changes in crop tissues, and cells. Furthermore, a single crop disease can show different symptoms. Usually, the differences in symptoms between early crop d...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/12/6/887 |
| _version_ | 1797490944258342912 |
|---|---|
| author | Jianwu Lin Xiaoyulong Chen Renyong Pan Tengbao Cao Jitong Cai Yang Chen Xishun Peng Tomislav Cernava Xin Zhang |
| author_facet | Jianwu Lin Xiaoyulong Chen Renyong Pan Tengbao Cao Jitong Cai Yang Chen Xishun Peng Tomislav Cernava Xin Zhang |
| author_sort | Jianwu Lin |
| collection | DOAJ |
| description | Most convolutional neural network (CNN) models have various difficulties in identifying crop diseases owing to morphological and physiological changes in crop tissues, and cells. Furthermore, a single crop disease can show different symptoms. Usually, the differences in symptoms between early crop disease and late crop disease stages include the area of disease and color of disease. This also poses additional difficulties for CNN models. Here, we propose a lightweight CNN model called GrapeNet for the identification of different symptom stages for specific grape diseases. The main components of GrapeNet are residual blocks, residual feature fusion blocks (RFFBs), and convolution block attention modules. The residual blocks are used to deepen the network depth and extract rich features. To alleviate the CNN performance degradation associated with a large number of hidden layers, we designed an RFFB module based on the residual block. It fuses the average pooled feature map before the residual block input and the high-dimensional feature maps after the residual block output by a concatenation operation, thereby achieving feature fusion at different depths. In addition, the convolutional block attention module (CBAM) is introduced after each RFFB module to extract valid disease information. The obtained results show that the identification accuracy was determined as 82.99%, 84.01%, 82.74%, 84.77%, 80.96%, 82.74%, 80.96%, 83.76%, and 86.29% for GoogLeNet, Vgg16, ResNet34, DenseNet121, MobileNetV2, MobileNetV3_large, ShuffleNetV2_×1.0, EfficientNetV2_s, and GrapeNet. The GrapeNet model achieved the best classification performance when compared with other classical models. The total number of parameters of the GrapeNet model only included 2.15 million. Compared with DenseNet121, which has the highest accuracy among classical network models, the number of parameters of GrapeNet was reduced by 4.81 million, thereby reducing the training time of GrapeNet by about two times compared with that of DenseNet121. Moreover, the visualization results of Grad-cam indicate that the introduction of CBAM can emphasize disease information and suppress irrelevant information. The overall results suggest that the GrapeNet model is useful for the automatic identification of grape leaf diseases. |
| first_indexed | 2024-03-10T00:40:18Z |
| format | Article |
| id | doaj.art-64df138992464865b08977469e4a3ff2 |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-10T00:40:18Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-64df138992464865b08977469e4a3ff22023-11-23T15:08:17ZengMDPI AGAgriculture2077-04722022-06-0112688710.3390/agriculture12060887GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf DiseasesJianwu Lin0Xiaoyulong Chen1Renyong Pan2Tengbao Cao3Jitong Cai4Yang Chen5Xishun Peng6Tomislav Cernava7Xin Zhang8College of Big Data and Information Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Tobacco Science, Guizhou University, Guiyang 550025, ChinaCollege of Big Data and Information Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Big Data and Information Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Big Data and Information Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Big Data and Information Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Big Data and Information Engineering, Guizhou University, Guiyang 550025, ChinaInstitute of Environmental Biotechnology, Graz University of Technology, 8010 Graz, AustriaCollege of Big Data and Information Engineering, Guizhou University, Guiyang 550025, ChinaMost convolutional neural network (CNN) models have various difficulties in identifying crop diseases owing to morphological and physiological changes in crop tissues, and cells. Furthermore, a single crop disease can show different symptoms. Usually, the differences in symptoms between early crop disease and late crop disease stages include the area of disease and color of disease. This also poses additional difficulties for CNN models. Here, we propose a lightweight CNN model called GrapeNet for the identification of different symptom stages for specific grape diseases. The main components of GrapeNet are residual blocks, residual feature fusion blocks (RFFBs), and convolution block attention modules. The residual blocks are used to deepen the network depth and extract rich features. To alleviate the CNN performance degradation associated with a large number of hidden layers, we designed an RFFB module based on the residual block. It fuses the average pooled feature map before the residual block input and the high-dimensional feature maps after the residual block output by a concatenation operation, thereby achieving feature fusion at different depths. In addition, the convolutional block attention module (CBAM) is introduced after each RFFB module to extract valid disease information. The obtained results show that the identification accuracy was determined as 82.99%, 84.01%, 82.74%, 84.77%, 80.96%, 82.74%, 80.96%, 83.76%, and 86.29% for GoogLeNet, Vgg16, ResNet34, DenseNet121, MobileNetV2, MobileNetV3_large, ShuffleNetV2_×1.0, EfficientNetV2_s, and GrapeNet. The GrapeNet model achieved the best classification performance when compared with other classical models. The total number of parameters of the GrapeNet model only included 2.15 million. Compared with DenseNet121, which has the highest accuracy among classical network models, the number of parameters of GrapeNet was reduced by 4.81 million, thereby reducing the training time of GrapeNet by about two times compared with that of DenseNet121. Moreover, the visualization results of Grad-cam indicate that the introduction of CBAM can emphasize disease information and suppress irrelevant information. The overall results suggest that the GrapeNet model is useful for the automatic identification of grape leaf diseases.https://www.mdpi.com/2077-0472/12/6/887convolutional neural networkresidual blockattention mechanismgrape leaf disease |
| spellingShingle | Jianwu Lin Xiaoyulong Chen Renyong Pan Tengbao Cao Jitong Cai Yang Chen Xishun Peng Tomislav Cernava Xin Zhang GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases Agriculture convolutional neural network residual block attention mechanism grape leaf disease |
| title | GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases |
| title_full | GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases |
| title_fullStr | GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases |
| title_full_unstemmed | GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases |
| title_short | GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases |
| title_sort | grapenet a lightweight convolutional neural network model for identification of grape leaf diseases |
| topic | convolutional neural network residual block attention mechanism grape leaf disease |
| url | https://www.mdpi.com/2077-0472/12/6/887 |
| work_keys_str_mv | AT jianwulin grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases AT xiaoyulongchen grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases AT renyongpan grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases AT tengbaocao grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases AT jitongcai grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases AT yangchen grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases AT xishunpeng grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases AT tomislavcernava grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases AT xinzhang grapenetalightweightconvolutionalneuralnetworkmodelforidentificationofgrapeleafdiseases |