Construction of deep learning-based disease detection model in plants
Abstract Accurately detecting disease occurrences of crops in early stage is essential for quality and yield of crops through the decision of an appropriate treatments. However, detection of disease needs specialized knowledge and long-term experiences in plant pathology. Thus, an automated system f...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-05-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-34549-2 |
| _version_ | 1827952743236501504 |
|---|---|
| author | Minah Jung Jong Seob Song Ah-Young Shin Beomjo Choi Sangjin Go Suk-Yoon Kwon Juhan Park Sung Goo Park Yong-Min Kim |
| author_facet | Minah Jung Jong Seob Song Ah-Young Shin Beomjo Choi Sangjin Go Suk-Yoon Kwon Juhan Park Sung Goo Park Yong-Min Kim |
| author_sort | Minah Jung |
| collection | DOAJ |
| description | Abstract Accurately detecting disease occurrences of crops in early stage is essential for quality and yield of crops through the decision of an appropriate treatments. However, detection of disease needs specialized knowledge and long-term experiences in plant pathology. Thus, an automated system for disease detecting in crops will play an important role in agriculture by constructing early detection system of disease. To develop this system, construction of a stepwise disease detection model using images of diseased-healthy plant pairs and a CNN algorithm consisting of five pre-trained models. The disease detection model consists of three step classification models, crop classification, disease detection, and disease classification. The ‘unknown’ is added into categories to generalize the model for wide application. In the validation test, the disease detection model classified crops and disease types with high accuracy (97.09%). The low accuracy of non-model crops was improved by adding these crops to the training dataset implicating expendability of the model. Our model has the potential to apply to smart farming of Solanaceae crops and will be widely used by adding more various crops as training dataset. |
| first_indexed | 2024-04-09T14:02:24Z |
| format | Article |
| id | doaj.art-9d670c43c63b4fde9d4393574d15967d |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T14:02:24Z |
| publishDate | 2023-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-9d670c43c63b4fde9d4393574d15967d2023-05-07T11:14:11ZengNature PortfolioScientific Reports2045-23222023-05-0113111310.1038/s41598-023-34549-2Construction of deep learning-based disease detection model in plantsMinah Jung0Jong Seob Song1Ah-Young Shin2Beomjo Choi3Sangjin Go4Suk-Yoon Kwon5Juhan Park6Sung Goo Park7Yong-Min Kim8Department of Functional Genomics, KRIBB School of Biological Science, Korea University of Science and Technology (UST)Euclidsoft Co., LtdPlant Systems Research Center, Korea Research Institute of Bioscience and Biotechnology (KRIBB)Plant Systems Research Center, Korea Research Institute of Bioscience and Biotechnology (KRIBB)Plant Systems Research Center, Korea Research Institute of Bioscience and Biotechnology (KRIBB)Plant Systems Research Center, Korea Research Institute of Bioscience and Biotechnology (KRIBB)Euclidsoft Co., LtdDepartment of Functional Genomics, KRIBB School of Biological Science, Korea University of Science and Technology (UST)Plant Systems Research Center, Korea Research Institute of Bioscience and Biotechnology (KRIBB)Abstract Accurately detecting disease occurrences of crops in early stage is essential for quality and yield of crops through the decision of an appropriate treatments. However, detection of disease needs specialized knowledge and long-term experiences in plant pathology. Thus, an automated system for disease detecting in crops will play an important role in agriculture by constructing early detection system of disease. To develop this system, construction of a stepwise disease detection model using images of diseased-healthy plant pairs and a CNN algorithm consisting of five pre-trained models. The disease detection model consists of three step classification models, crop classification, disease detection, and disease classification. The ‘unknown’ is added into categories to generalize the model for wide application. In the validation test, the disease detection model classified crops and disease types with high accuracy (97.09%). The low accuracy of non-model crops was improved by adding these crops to the training dataset implicating expendability of the model. Our model has the potential to apply to smart farming of Solanaceae crops and will be widely used by adding more various crops as training dataset.https://doi.org/10.1038/s41598-023-34549-2 |
| spellingShingle | Minah Jung Jong Seob Song Ah-Young Shin Beomjo Choi Sangjin Go Suk-Yoon Kwon Juhan Park Sung Goo Park Yong-Min Kim Construction of deep learning-based disease detection model in plants Scientific Reports |
| title | Construction of deep learning-based disease detection model in plants |
| title_full | Construction of deep learning-based disease detection model in plants |
| title_fullStr | Construction of deep learning-based disease detection model in plants |
| title_full_unstemmed | Construction of deep learning-based disease detection model in plants |
| title_short | Construction of deep learning-based disease detection model in plants |
| title_sort | construction of deep learning based disease detection model in plants |
| url | https://doi.org/10.1038/s41598-023-34549-2 |
| work_keys_str_mv | AT minahjung constructionofdeeplearningbaseddiseasedetectionmodelinplants AT jongseobsong constructionofdeeplearningbaseddiseasedetectionmodelinplants AT ahyoungshin constructionofdeeplearningbaseddiseasedetectionmodelinplants AT beomjochoi constructionofdeeplearningbaseddiseasedetectionmodelinplants AT sangjingo constructionofdeeplearningbaseddiseasedetectionmodelinplants AT sukyoonkwon constructionofdeeplearningbaseddiseasedetectionmodelinplants AT juhanpark constructionofdeeplearningbaseddiseasedetectionmodelinplants AT sunggoopark constructionofdeeplearningbaseddiseasedetectionmodelinplants AT yongminkim constructionofdeeplearningbaseddiseasedetectionmodelinplants |