Intelligent diagnosis of northern corn leaf blight with deep learning model
Maize (Zea mays L.), also known as corn, is the third most cultivated crop in the world. Northern corn leaf blight (NCLB) is a globally devastating maize foliar disease caused by Setosphaeria turcica (Luttrell) Leonard and Suggs. Early intelligent diagnosis and warning is an effective and economical...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-04-01
|
| Series: | Journal of Integrative Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095311921637073 |
| _version_ | 1818157372055486464 |
|---|---|
| author | Shuai-qun PAN Jing-fen QIAO Rui WANG Hui-lin YU Cheng WANG Kerry TAYLOR Hong-yu PAN |
| author_facet | Shuai-qun PAN Jing-fen QIAO Rui WANG Hui-lin YU Cheng WANG Kerry TAYLOR Hong-yu PAN |
| author_sort | Shuai-qun PAN |
| collection | DOAJ |
| description | Maize (Zea mays L.), also known as corn, is the third most cultivated crop in the world. Northern corn leaf blight (NCLB) is a globally devastating maize foliar disease caused by Setosphaeria turcica (Luttrell) Leonard and Suggs. Early intelligent diagnosis and warning is an effective and economical strategy to control this disease. Today, deep learning is beginning to play an essential role in agriculture. Notably, deep convolutional neural networks (DCNN) are amongst the most successful machine learning techniques in plant disease detection and diagnosis. Our study aims to identify NCLB in the maize-producing area in Jilin Province based on several DCNN models. We established a database of 985 leaf images of healthy and infected maize and applied data augmentation techniques including image segmentation, image resizing, image cropping, and image transformation, to expand to 30 655 images. Several proven convolutional neural networks, such as AlexNet, GoogleNet, VGG16, and VGG19, were then used to identify diseases. Based on the best performance of the DCNN pre-trained model GoogleNet, some of the recent loss functions developed for deep facial recognition tasks such as ArcFace, CosFace, and A-Softmax were applied to detect NCLB. We found that a pre-trained GoogleNet architecture with the Softmax loss function can achieve an excellent accuracy of 99.94% on NCLB diagnosis. The analysis was implemented in Python with two deep learning frameworks, Pytorch and Keras. The techniques, training, validation, and test results are presented in this paper. Overall, our study explores intelligent identification technology for NCLB and effectively diagnoses NCLB from images of maize. |
| first_indexed | 2024-12-11T15:13:08Z |
| format | Article |
| id | doaj.art-5a2de7d96d9a43ca84c4123e0dd67cd4 |
| institution | Directory Open Access Journal |
| issn | 2095-3119 |
| language | English |
| last_indexed | 2024-12-11T15:13:08Z |
| publishDate | 2022-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Integrative Agriculture |
| spelling | doaj.art-5a2de7d96d9a43ca84c4123e0dd67cd42022-12-22T01:00:41ZengElsevierJournal of Integrative Agriculture2095-31192022-04-0121410941105Intelligent diagnosis of northern corn leaf blight with deep learning modelShuai-qun PAN0Jing-fen QIAO1Rui WANG2Hui-lin YU3Cheng WANG4Kerry TAYLOR5Hong-yu PAN6School of Computing, Australian National University, Canberra 2601, AustraliaSchool of Computing, Australian National University, Canberra 2601, AustraliaCollege of Plant Sciences, Jilin University, Changchun 130062, P.R.ChinaCollege of Plant Sciences, Jilin University, Changchun 130062, P.R.ChinaCollege of Plant Sciences, Jilin University, Changchun 130062, P.R.ChinaSchool of Computing, Australian National University, Canberra 2601, AustraliaCollege of Plant Sciences, Jilin University, Changchun 130062, P.R.China; Correspondence PAN Hong-yu, Tel/Fax: +86-431-87835659Maize (Zea mays L.), also known as corn, is the third most cultivated crop in the world. Northern corn leaf blight (NCLB) is a globally devastating maize foliar disease caused by Setosphaeria turcica (Luttrell) Leonard and Suggs. Early intelligent diagnosis and warning is an effective and economical strategy to control this disease. Today, deep learning is beginning to play an essential role in agriculture. Notably, deep convolutional neural networks (DCNN) are amongst the most successful machine learning techniques in plant disease detection and diagnosis. Our study aims to identify NCLB in the maize-producing area in Jilin Province based on several DCNN models. We established a database of 985 leaf images of healthy and infected maize and applied data augmentation techniques including image segmentation, image resizing, image cropping, and image transformation, to expand to 30 655 images. Several proven convolutional neural networks, such as AlexNet, GoogleNet, VGG16, and VGG19, were then used to identify diseases. Based on the best performance of the DCNN pre-trained model GoogleNet, some of the recent loss functions developed for deep facial recognition tasks such as ArcFace, CosFace, and A-Softmax were applied to detect NCLB. We found that a pre-trained GoogleNet architecture with the Softmax loss function can achieve an excellent accuracy of 99.94% on NCLB diagnosis. The analysis was implemented in Python with two deep learning frameworks, Pytorch and Keras. The techniques, training, validation, and test results are presented in this paper. Overall, our study explores intelligent identification technology for NCLB and effectively diagnoses NCLB from images of maize.http://www.sciencedirect.com/science/article/pii/S2095311921637073maizenorthern corn leaf blightSetosphaeria turcicaintelligent diagnosisdeep learningconvolutional neural network |
| spellingShingle | Shuai-qun PAN Jing-fen QIAO Rui WANG Hui-lin YU Cheng WANG Kerry TAYLOR Hong-yu PAN Intelligent diagnosis of northern corn leaf blight with deep learning model Journal of Integrative Agriculture maize northern corn leaf blight Setosphaeria turcica intelligent diagnosis deep learning convolutional neural network |
| title | Intelligent diagnosis of northern corn leaf blight with deep learning model |
| title_full | Intelligent diagnosis of northern corn leaf blight with deep learning model |
| title_fullStr | Intelligent diagnosis of northern corn leaf blight with deep learning model |
| title_full_unstemmed | Intelligent diagnosis of northern corn leaf blight with deep learning model |
| title_short | Intelligent diagnosis of northern corn leaf blight with deep learning model |
| title_sort | intelligent diagnosis of northern corn leaf blight with deep learning model |
| topic | maize northern corn leaf blight Setosphaeria turcica intelligent diagnosis deep learning convolutional neural network |
| url | http://www.sciencedirect.com/science/article/pii/S2095311921637073 |
| work_keys_str_mv | AT shuaiqunpan intelligentdiagnosisofnortherncornleafblightwithdeeplearningmodel AT jingfenqiao intelligentdiagnosisofnortherncornleafblightwithdeeplearningmodel AT ruiwang intelligentdiagnosisofnortherncornleafblightwithdeeplearningmodel AT huilinyu intelligentdiagnosisofnortherncornleafblightwithdeeplearningmodel AT chengwang intelligentdiagnosisofnortherncornleafblightwithdeeplearningmodel AT kerrytaylor intelligentdiagnosisofnortherncornleafblightwithdeeplearningmodel AT hongyupan intelligentdiagnosisofnortherncornleafblightwithdeeplearningmodel |