Construction of Apple Leaf Diseases Identification Networks Based on Xception Fused by SE Module
The fast and accurate identification of apple leaf diseases is beneficial for disease control and management of apple orchards. An improved network for apple leaf disease classification and a lightweight model for mobile terminal usage was designed in this paper. First, we proposed SE-DEEP block to...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/10/4614 |
| _version_ | 1827692239684370432 |
|---|---|
| author | Xiaofei Chao Xiao Hu Jingze Feng Zhao Zhang Meili Wang Dongjian He |
| author_facet | Xiaofei Chao Xiao Hu Jingze Feng Zhao Zhang Meili Wang Dongjian He |
| author_sort | Xiaofei Chao |
| collection | DOAJ |
| description | The fast and accurate identification of apple leaf diseases is beneficial for disease control and management of apple orchards. An improved network for apple leaf disease classification and a lightweight model for mobile terminal usage was designed in this paper. First, we proposed SE-DEEP block to fuse the Squeeze-and-Excitation (SE) module with the Xception network to get the SE_Xception network, where the SE module is inserted between the depth-wise convolution and point-wise convolution of the depth-wise separable convolution layer. Therefore, the feature channels from the lower layers could be directly weighted, which made the model more sensitive to the principal features of the classification task. Second, we designed a lightweight network, named SE_miniXception, by reducing the depth and width of SE_Xception. Experimental results show that the average classification accuracy of SE_Xception is 99.40%, which is 1.99% higher than Xception. The average classification accuracy of SE_miniXception is 97.01%, which is 1.60% and 1.22% higher than MobileNetV1 and ShuffleNet, respectively, while its number of parameters is less than those of MobileNet and ShuffleNet. The minimized network decreases the memory usage and FLOPs, and accelerates the recognition speed from 15 to 7 milliseconds per image. Our proposed SE-DEEP block provides a choice for improving network accuracy and our network compression scheme provides ideas to lightweight existing networks. |
| first_indexed | 2024-03-10T11:18:34Z |
| format | Article |
| id | doaj.art-e749813dced24b6d99c466b0b4470818 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T11:18:34Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e749813dced24b6d99c466b0b44708182023-11-21T20:17:13ZengMDPI AGApplied Sciences2076-34172021-05-011110461410.3390/app11104614Construction of Apple Leaf Diseases Identification Networks Based on Xception Fused by SE ModuleXiaofei Chao0Xiao Hu1Jingze Feng2Zhao Zhang3Meili Wang4Dongjian He5College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, Shanxi, ChinaCollege of Information Engineering, Northwest A&F University, Yangling 712100, Shanxi, ChinaCollege of Information Engineering, Northwest A&F University, Yangling 712100, Shanxi, ChinaCollege of Information Engineering, Northwest A&F University, Yangling 712100, Shanxi, ChinaCollege of Information Engineering, Northwest A&F University, Yangling 712100, Shanxi, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, Shanxi, ChinaThe fast and accurate identification of apple leaf diseases is beneficial for disease control and management of apple orchards. An improved network for apple leaf disease classification and a lightweight model for mobile terminal usage was designed in this paper. First, we proposed SE-DEEP block to fuse the Squeeze-and-Excitation (SE) module with the Xception network to get the SE_Xception network, where the SE module is inserted between the depth-wise convolution and point-wise convolution of the depth-wise separable convolution layer. Therefore, the feature channels from the lower layers could be directly weighted, which made the model more sensitive to the principal features of the classification task. Second, we designed a lightweight network, named SE_miniXception, by reducing the depth and width of SE_Xception. Experimental results show that the average classification accuracy of SE_Xception is 99.40%, which is 1.99% higher than Xception. The average classification accuracy of SE_miniXception is 97.01%, which is 1.60% and 1.22% higher than MobileNetV1 and ShuffleNet, respectively, while its number of parameters is less than those of MobileNet and ShuffleNet. The minimized network decreases the memory usage and FLOPs, and accelerates the recognition speed from 15 to 7 milliseconds per image. Our proposed SE-DEEP block provides a choice for improving network accuracy and our network compression scheme provides ideas to lightweight existing networks.https://www.mdpi.com/2076-3417/11/10/4614apple leaf diseasedisease identification networkXceptionchannel attentionlightweight network |
| spellingShingle | Xiaofei Chao Xiao Hu Jingze Feng Zhao Zhang Meili Wang Dongjian He Construction of Apple Leaf Diseases Identification Networks Based on Xception Fused by SE Module Applied Sciences apple leaf disease disease identification network Xception channel attention lightweight network |
| title | Construction of Apple Leaf Diseases Identification Networks Based on Xception Fused by SE Module |
| title_full | Construction of Apple Leaf Diseases Identification Networks Based on Xception Fused by SE Module |
| title_fullStr | Construction of Apple Leaf Diseases Identification Networks Based on Xception Fused by SE Module |
| title_full_unstemmed | Construction of Apple Leaf Diseases Identification Networks Based on Xception Fused by SE Module |
| title_short | Construction of Apple Leaf Diseases Identification Networks Based on Xception Fused by SE Module |
| title_sort | construction of apple leaf diseases identification networks based on xception fused by se module |
| topic | apple leaf disease disease identification network Xception channel attention lightweight network |
| url | https://www.mdpi.com/2076-3417/11/10/4614 |
| work_keys_str_mv | AT xiaofeichao constructionofappleleafdiseasesidentificationnetworksbasedonxceptionfusedbysemodule AT xiaohu constructionofappleleafdiseasesidentificationnetworksbasedonxceptionfusedbysemodule AT jingzefeng constructionofappleleafdiseasesidentificationnetworksbasedonxceptionfusedbysemodule AT zhaozhang constructionofappleleafdiseasesidentificationnetworksbasedonxceptionfusedbysemodule AT meiliwang constructionofappleleafdiseasesidentificationnetworksbasedonxceptionfusedbysemodule AT dongjianhe constructionofappleleafdiseasesidentificationnetworksbasedonxceptionfusedbysemodule |