Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network
Disease has always been one of the main reasons for the decline of apple quality and yield, which directly harms the development of agricultural economy. Therefore, precise diagnosis of apple diseases and correct decision making are important measures to reduce agricultural losses and promote econom...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-10-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2021.698474/full |
| _version_ | 1819133623525179392 |
|---|---|
| author | Yunong Tian Yunong Tian En Li En Li Zize Liang Zize Liang Min Tan Min Tan Xiongkui He |
| author_facet | Yunong Tian Yunong Tian En Li En Li Zize Liang Zize Liang Min Tan Min Tan Xiongkui He |
| author_sort | Yunong Tian |
| collection | DOAJ |
| description | Disease has always been one of the main reasons for the decline of apple quality and yield, which directly harms the development of agricultural economy. Therefore, precise diagnosis of apple diseases and correct decision making are important measures to reduce agricultural losses and promote economic growth. In this paper, a novel Multi-scale Dense classification network is adopted to realize the diagnosis of 11 types of images, including healthy and diseased apple fruits and leaves. The diagnosis of different kinds of diseases and the same disease with different grades was accomplished. First of all, to solve the problem of insufficient images of anthracnose and ring rot, Cycle-GAN algorithm was applied to achieve dataset expansion on the basis of traditional image augmentation methods. Cycle-GAN learned the image characteristics of healthy apples and diseased apples to generate anthracnose and ring rot lesions on the surface of healthy apple fruits. The diseased apple images generated by Cycle-GAN were added to the training set, which improved the diagnosis performance compared with other traditional image augmentation methods. Subsequently, DenseNet and Multi-scale connection were adopted to establish two kinds of models, Multi-scale Dense Inception-V4 and Multi-scale Dense Inception-Resnet-V2, which facilitated the reuse of image features of the bottom layers in the classification neural networks. Both models accomplished the diagnosis of 11 different types of images. The classification accuracy was 94.31 and 94.74%, respectively, which exceeded DenseNet-121 network and reached the state-of-the-art level. |
| first_indexed | 2024-12-22T09:50:14Z |
| format | Article |
| id | doaj.art-19ab962e5757449aa9e5bd05ffa05175 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-12-22T09:50:14Z |
| publishDate | 2021-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-19ab962e5757449aa9e5bd05ffa051752022-12-21T18:30:23ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2021-10-011210.3389/fpls.2021.698474698474Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification NetworkYunong Tian0Yunong Tian1En Li2En Li3Zize Liang4Zize Liang5Min Tan6Min Tan7Xiongkui He8State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaCollege of Science, China Agricultural University, Beijing, ChinaDisease has always been one of the main reasons for the decline of apple quality and yield, which directly harms the development of agricultural economy. Therefore, precise diagnosis of apple diseases and correct decision making are important measures to reduce agricultural losses and promote economic growth. In this paper, a novel Multi-scale Dense classification network is adopted to realize the diagnosis of 11 types of images, including healthy and diseased apple fruits and leaves. The diagnosis of different kinds of diseases and the same disease with different grades was accomplished. First of all, to solve the problem of insufficient images of anthracnose and ring rot, Cycle-GAN algorithm was applied to achieve dataset expansion on the basis of traditional image augmentation methods. Cycle-GAN learned the image characteristics of healthy apples and diseased apples to generate anthracnose and ring rot lesions on the surface of healthy apple fruits. The diseased apple images generated by Cycle-GAN were added to the training set, which improved the diagnosis performance compared with other traditional image augmentation methods. Subsequently, DenseNet and Multi-scale connection were adopted to establish two kinds of models, Multi-scale Dense Inception-V4 and Multi-scale Dense Inception-Resnet-V2, which facilitated the reuse of image features of the bottom layers in the classification neural networks. Both models accomplished the diagnosis of 11 different types of images. The classification accuracy was 94.31 and 94.74%, respectively, which exceeded DenseNet-121 network and reached the state-of-the-art level.https://www.frontiersin.org/articles/10.3389/fpls.2021.698474/fullapple disease diagnosisCycle-GANMulti-scale connectionDenseNetdeep learning |
| spellingShingle | Yunong Tian Yunong Tian En Li En Li Zize Liang Zize Liang Min Tan Min Tan Xiongkui He Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network Frontiers in Plant Science apple disease diagnosis Cycle-GAN Multi-scale connection DenseNet deep learning |
| title | Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network |
| title_full | Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network |
| title_fullStr | Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network |
| title_full_unstemmed | Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network |
| title_short | Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network |
| title_sort | diagnosis of typical apple diseases a deep learning method based on multi scale dense classification network |
| topic | apple disease diagnosis Cycle-GAN Multi-scale connection DenseNet deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2021.698474/full |
| work_keys_str_mv | AT yunongtian diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork AT yunongtian diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork AT enli diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork AT enli diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork AT zizeliang diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork AT zizeliang diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork AT mintan diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork AT mintan diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork AT xiongkuihe diagnosisoftypicalapplediseasesadeeplearningmethodbasedonmultiscaledenseclassificationnetwork |