Mobile Plant Disease Classifier, Trained with a Small Number of Images by the End User
Mobile applications that can be used for the training and classification of plant diseases are described in this paper. Professional agronomists can select the species and their diseases that are supported by the developed tool and follow an automatic training procedure using a small number of indic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/12/8/1732 |
| _version_ | 1827618319287451648 |
|---|---|
| author | Nikos Petrellis Christos Antonopoulos Georgios Keramidas Nikolaos Voros |
| author_facet | Nikos Petrellis Christos Antonopoulos Georgios Keramidas Nikolaos Voros |
| author_sort | Nikos Petrellis |
| collection | DOAJ |
| description | Mobile applications that can be used for the training and classification of plant diseases are described in this paper. Professional agronomists can select the species and their diseases that are supported by the developed tool and follow an automatic training procedure using a small number of indicative photographs. The employed classification method is based on features that represent distinct aspects of the sick plant such as, for example, the color level distribution in the regions of interest. These features are extracted from photographs that display a plant part such as a leaf or a fruit. Multiple reference ranges are determined for each feature during training. When a new photograph is analyzed, its feature values are compared with the reference ranges, and different grades are assigned depending on whether a feature value falls within a range or not. The new photograph is classified as the disease with the highest grade. Ten tomato diseases are used as a case study, and the applications are trained with 40–100 segmented and normalized photographs for each disease. An accuracy between 93.4% and 96.1% is experimentally measured in this case. An additional dataset of pear disease photographs that are not segmented or normalized is also tested with an average accuracy of 95%. |
| first_indexed | 2024-03-09T10:03:54Z |
| format | Article |
| id | doaj.art-e4e7231ce9964883a856421a5160e114 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-09T10:03:54Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-e4e7231ce9964883a856421a5160e1142023-12-01T23:17:16ZengMDPI AGAgronomy2073-43952022-07-01128173210.3390/agronomy12081732Mobile Plant Disease Classifier, Trained with a Small Number of Images by the End UserNikos Petrellis0Christos Antonopoulos1Georgios Keramidas2Nikolaos Voros3Embedded System Design & Automations Lab (ESDALAB), Electrical and Computer Engineering Department, University of Peloponnese, 26334 Patras, GreeceEmbedded System Design & Automations Lab (ESDALAB), Electrical and Computer Engineering Department, University of Peloponnese, 26334 Patras, GreeceSchool of Informatics, Aristotle University of Thessaloniki, 54642 Thessaloniki, GreeceEmbedded System Design & Automations Lab (ESDALAB), Electrical and Computer Engineering Department, University of Peloponnese, 26334 Patras, GreeceMobile applications that can be used for the training and classification of plant diseases are described in this paper. Professional agronomists can select the species and their diseases that are supported by the developed tool and follow an automatic training procedure using a small number of indicative photographs. The employed classification method is based on features that represent distinct aspects of the sick plant such as, for example, the color level distribution in the regions of interest. These features are extracted from photographs that display a plant part such as a leaf or a fruit. Multiple reference ranges are determined for each feature during training. When a new photograph is analyzed, its feature values are compared with the reference ranges, and different grades are assigned depending on whether a feature value falls within a range or not. The new photograph is classified as the disease with the highest grade. Ten tomato diseases are used as a case study, and the applications are trained with 40–100 segmented and normalized photographs for each disease. An accuracy between 93.4% and 96.1% is experimentally measured in this case. An additional dataset of pear disease photographs that are not segmented or normalized is also tested with an average accuracy of 95%.https://www.mdpi.com/2073-4395/12/8/1732disease classificationtrainingmobile applicationimage processingsegmentationtomato diseases |
| spellingShingle | Nikos Petrellis Christos Antonopoulos Georgios Keramidas Nikolaos Voros Mobile Plant Disease Classifier, Trained with a Small Number of Images by the End User Agronomy disease classification training mobile application image processing segmentation tomato diseases |
| title | Mobile Plant Disease Classifier, Trained with a Small Number of Images by the End User |
| title_full | Mobile Plant Disease Classifier, Trained with a Small Number of Images by the End User |
| title_fullStr | Mobile Plant Disease Classifier, Trained with a Small Number of Images by the End User |
| title_full_unstemmed | Mobile Plant Disease Classifier, Trained with a Small Number of Images by the End User |
| title_short | Mobile Plant Disease Classifier, Trained with a Small Number of Images by the End User |
| title_sort | mobile plant disease classifier trained with a small number of images by the end user |
| topic | disease classification training mobile application image processing segmentation tomato diseases |
| url | https://www.mdpi.com/2073-4395/12/8/1732 |
| work_keys_str_mv | AT nikospetrellis mobileplantdiseaseclassifiertrainedwithasmallnumberofimagesbytheenduser AT christosantonopoulos mobileplantdiseaseclassifiertrainedwithasmallnumberofimagesbytheenduser AT georgioskeramidas mobileplantdiseaseclassifiertrainedwithasmallnumberofimagesbytheenduser AT nikolaosvoros mobileplantdiseaseclassifiertrainedwithasmallnumberofimagesbytheenduser |