Effects of Different Pre-Trained Deep Learning Algorithms as Feature Extractor in Tomato Plant Health Classification
This is a challenge to identify tomato plant diseases using naked eyes. In implementing an automation plantation system, a plant health classification system is necessary in monitoring the health of the plants. This study proposes a system that can classify tomato plant health into five categories o...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
-
2023
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/9266/1/J16084_6c08d828d34b1a281bdc492009add2c0.pdf |
| _version_ | 1825710731855659008 |
|---|---|
| author | Hou Ming Chong, Hou Ming Chong Xien Yin Yap, Xien Yin Yap Kim Seng Chia, Kim Seng Chia |
| author_facet | Hou Ming Chong, Hou Ming Chong Xien Yin Yap, Xien Yin Yap Kim Seng Chia, Kim Seng Chia |
| author_sort | Hou Ming Chong, Hou Ming Chong |
| collection | UTHM |
| description | This is a challenge to identify tomato plant diseases using naked eyes. In implementing an automation plantation system, a plant health classification system is necessary in monitoring the health of the plants. This study proposes a system that can classify tomato plant health into five categories of healthy, early blight, late blight, bacterial spot, and yellow leaf curl virus based on their leaves using deep learning algorithms as feature extractors. Five different pre-trained deep learning algorithms (i.e. Resnet-50, AlexNet, GoogleNet, VGG16, and VGG19) were studied and compared. A Raspberry Pi coupled with a camera was proposed to
capture tomato plant leaf image. After that, a support vector machine (SVM) with the extracted features was trained for the plant health classification. The results indicate that SVM coupled with ResNet-50 was the best with averaged training and testing accuracies of 98.26 and 93.33%, respectively. |
| first_indexed | 2024-03-05T22:02:05Z |
| format | Article |
| id | uthm.eprints-9266 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-03-05T22:02:05Z |
| publishDate | 2023 |
| publisher | - |
| record_format | dspace |
| spelling | uthm.eprints-92662023-07-17T07:46:51Z http://eprints.uthm.edu.my/9266/ Effects of Different Pre-Trained Deep Learning Algorithms as Feature Extractor in Tomato Plant Health Classification Hou Ming Chong, Hou Ming Chong Xien Yin Yap, Xien Yin Yap Kim Seng Chia, Kim Seng Chia T Technology (General) This is a challenge to identify tomato plant diseases using naked eyes. In implementing an automation plantation system, a plant health classification system is necessary in monitoring the health of the plants. This study proposes a system that can classify tomato plant health into five categories of healthy, early blight, late blight, bacterial spot, and yellow leaf curl virus based on their leaves using deep learning algorithms as feature extractors. Five different pre-trained deep learning algorithms (i.e. Resnet-50, AlexNet, GoogleNet, VGG16, and VGG19) were studied and compared. A Raspberry Pi coupled with a camera was proposed to capture tomato plant leaf image. After that, a support vector machine (SVM) with the extracted features was trained for the plant health classification. The results indicate that SVM coupled with ResNet-50 was the best with averaged training and testing accuracies of 98.26 and 93.33%, respectively. - 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/9266/1/J16084_6c08d828d34b1a281bdc492009add2c0.pdf Hou Ming Chong, Hou Ming Chong and Xien Yin Yap, Xien Yin Yap and Kim Seng Chia, Kim Seng Chia (2023) Effects of Different Pre-Trained Deep Learning Algorithms as Feature Extractor in Tomato Plant Health Classification. PATTERN RECOGNITION AND IMAGE ANALYSIS AUTOMATED SYSTEMS, HARDWARE AND SOFTWARE, 33 (1). pp. 12-19. https://doi.org/10.1134/S1054661823010017 |
| spellingShingle | T Technology (General) Hou Ming Chong, Hou Ming Chong Xien Yin Yap, Xien Yin Yap Kim Seng Chia, Kim Seng Chia Effects of Different Pre-Trained Deep Learning Algorithms as Feature Extractor in Tomato Plant Health Classification |
| title | Effects of Different Pre-Trained Deep Learning Algorithms
as Feature Extractor in Tomato Plant Health Classification |
| title_full | Effects of Different Pre-Trained Deep Learning Algorithms
as Feature Extractor in Tomato Plant Health Classification |
| title_fullStr | Effects of Different Pre-Trained Deep Learning Algorithms
as Feature Extractor in Tomato Plant Health Classification |
| title_full_unstemmed | Effects of Different Pre-Trained Deep Learning Algorithms
as Feature Extractor in Tomato Plant Health Classification |
| title_short | Effects of Different Pre-Trained Deep Learning Algorithms
as Feature Extractor in Tomato Plant Health Classification |
| title_sort | effects of different pre trained deep learning algorithms as feature extractor in tomato plant health classification |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/9266/1/J16084_6c08d828d34b1a281bdc492009add2c0.pdf |
| work_keys_str_mv | AT houmingchonghoumingchong effectsofdifferentpretraineddeeplearningalgorithmsasfeatureextractorintomatoplanthealthclassification AT xienyinyapxienyinyap effectsofdifferentpretraineddeeplearningalgorithmsasfeatureextractorintomatoplanthealthclassification AT kimsengchiakimsengchia effectsofdifferentpretraineddeeplearningalgorithmsasfeatureextractorintomatoplanthealthclassification |