A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry Leaves
Gray mold disease is one of the most frequently occurring diseases in strawberries. Given that it spreads rapidly, rapid countermeasures are necessary through the development of early diagnosis technology. In this study, hyperspectral images of strawberry leaves that were inoculated with gray mold f...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-03-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.837020/full |
| _version_ | 1819121258181165056 |
|---|---|
| author | Dae-Hyun Jung Jeong Do Kim Ho-Youn Kim Taek Sung Lee Hyoung Seok Kim Soo Hyun Park |
| author_facet | Dae-Hyun Jung Jeong Do Kim Ho-Youn Kim Taek Sung Lee Hyoung Seok Kim Soo Hyun Park |
| author_sort | Dae-Hyun Jung |
| collection | DOAJ |
| description | Gray mold disease is one of the most frequently occurring diseases in strawberries. Given that it spreads rapidly, rapid countermeasures are necessary through the development of early diagnosis technology. In this study, hyperspectral images of strawberry leaves that were inoculated with gray mold fungus to cause disease were taken; these images were classified into healthy and infected areas as seen by the naked eye. The areas where the infection spread after time elapsed were classified as the asymptomatic class. Square regions of interest (ROIs) with a dimensionality of 16 × 16 × 150 were acquired as training data, including infected, asymptomatic, and healthy areas. Then, 2D and 3D data were used in the development of a convolutional neural network (CNN) classification model. An effective wavelength analysis was performed before the development of the CNN model. Further, the classification model that was developed with 2D training data showed a classification accuracy of 0.74, while the model that used 3D data acquired an accuracy of 0.84; this indicated that the 3D data produced slightly better performance. When performing classification between healthy and asymptomatic areas for developing early diagnosis technology, the two CNN models showed a classification accuracy of 0.73 with regards to the asymptomatic ones. To increase accuracy in classifying asymptomatic areas, a model was developed by smoothing the spectrum data and expanding the first and second derivatives; the results showed that it was possible to increase the asymptomatic classification accuracy to 0.77 and reduce the misclassification of asymptomatic areas as healthy areas. Based on these results, it is concluded that the proposed 3D CNN classification model can be used as an early diagnosis sensor of gray mold diseases since it produces immediate on-site analysis results of hyperspectral images of leaves. |
| first_indexed | 2024-12-22T06:33:42Z |
| format | Article |
| id | doaj.art-3ea92db6bb3344d29508c1a02ec4c54d |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-12-22T06:33:42Z |
| publishDate | 2022-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-3ea92db6bb3344d29508c1a02ec4c54d2022-12-21T18:35:39ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-03-011310.3389/fpls.2022.837020837020A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry LeavesDae-Hyun JungJeong Do KimHo-Youn KimTaek Sung LeeHyoung Seok KimSoo Hyun ParkGray mold disease is one of the most frequently occurring diseases in strawberries. Given that it spreads rapidly, rapid countermeasures are necessary through the development of early diagnosis technology. In this study, hyperspectral images of strawberry leaves that were inoculated with gray mold fungus to cause disease were taken; these images were classified into healthy and infected areas as seen by the naked eye. The areas where the infection spread after time elapsed were classified as the asymptomatic class. Square regions of interest (ROIs) with a dimensionality of 16 × 16 × 150 were acquired as training data, including infected, asymptomatic, and healthy areas. Then, 2D and 3D data were used in the development of a convolutional neural network (CNN) classification model. An effective wavelength analysis was performed before the development of the CNN model. Further, the classification model that was developed with 2D training data showed a classification accuracy of 0.74, while the model that used 3D data acquired an accuracy of 0.84; this indicated that the 3D data produced slightly better performance. When performing classification between healthy and asymptomatic areas for developing early diagnosis technology, the two CNN models showed a classification accuracy of 0.73 with regards to the asymptomatic ones. To increase accuracy in classifying asymptomatic areas, a model was developed by smoothing the spectrum data and expanding the first and second derivatives; the results showed that it was possible to increase the asymptomatic classification accuracy to 0.77 and reduce the misclassification of asymptomatic areas as healthy areas. Based on these results, it is concluded that the proposed 3D CNN classification model can be used as an early diagnosis sensor of gray mold diseases since it produces immediate on-site analysis results of hyperspectral images of leaves.https://www.frontiersin.org/articles/10.3389/fpls.2022.837020/fullhyperspectral imagingstrawberry gray moldearly diagnosisasymptomatic infection3D convolutional neural network |
| spellingShingle | Dae-Hyun Jung Jeong Do Kim Ho-Youn Kim Taek Sung Lee Hyoung Seok Kim Soo Hyun Park A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry Leaves Frontiers in Plant Science hyperspectral imaging strawberry gray mold early diagnosis asymptomatic infection 3D convolutional neural network |
| title | A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry Leaves |
| title_full | A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry Leaves |
| title_fullStr | A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry Leaves |
| title_full_unstemmed | A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry Leaves |
| title_short | A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry Leaves |
| title_sort | hyperspectral data 3d convolutional neural network classification model for diagnosis of gray mold disease in strawberry leaves |
| topic | hyperspectral imaging strawberry gray mold early diagnosis asymptomatic infection 3D convolutional neural network |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2022.837020/full |
| work_keys_str_mv | AT daehyunjung ahyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT jeongdokim ahyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT hoyounkim ahyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT taeksunglee ahyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT hyoungseokkim ahyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT soohyunpark ahyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT daehyunjung hyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT jeongdokim hyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT hoyounkim hyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT taeksunglee hyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT hyoungseokkim hyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves AT soohyunpark hyperspectraldata3dconvolutionalneuralnetworkclassificationmodelfordiagnosisofgraymolddiseaseinstrawberryleaves |