TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS FEATURE EXTRACTORS FOR CHILI LEAF IMAGES
Chili is a popular crop that is widely grown due to its flavorful and spicy fruit that is nutritionally beneficial. For the benefit of economic growth, it is important to precisely assess the chili health. With the advancement of computer vision-based applications, methods such as feature descriptor...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
2024
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/12279/1/J17714_a2078c02b50c385a1088ef4c2b5ec6c0.pdf http://eprints.uthm.edu.my/12279/ https://doi.org/10.11113/jurnalteknologi.v86.19853%7C |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833419755916099584 |
|---|---|
| author | Aminuddin, Nuramin Fitri Abdul Kadir, Herdawatie Md Tomari, Mohd Razali Joret, Ariffuddin Tukiran, Zarina |
| author_facet | Aminuddin, Nuramin Fitri Abdul Kadir, Herdawatie Md Tomari, Mohd Razali Joret, Ariffuddin Tukiran, Zarina |
| author_sort | Aminuddin, Nuramin Fitri |
| building | UTHM Library |
| collection | Institutional Repository |
| content_provider | Universiti Tun Hussein Onn Malaysia |
| content_source | UTHM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | Chili is a popular crop that is widely grown due to its flavorful and spicy fruit that is nutritionally beneficial. For the benefit of economic growth, it is important to precisely assess the chili health. With the advancement of computer vision-based applications, methods such as feature descriptors have been utilized to assist farm owners in identifying chili diseases via chili leaf images. However, these feature descriptors still require the manual extraction of disease features in order to
accurately identify chili diseases. In this research, pretrained Convolutional Neural Networks (CNNs) are proposed as feature extractors to identify healthy and diseased chili leaf images. Three pretrained CNN models, DenseNet-201, EfficientNet-b0, and NasNet-Mobile, are utilized for their
ability to identify healthy and diseased chili leaf using five indexes: accuracy, recall, specificity, precision, and F1-score. These indexes are validated through a five-fold cross-validation method during the experiments. The experimental results show that the EfficientNet-b0 model achieved the
highest identification performance, with indexes of accuracy, recall, specificity, precision, and F1- score of 97.05%, 0.97, 0.92, 0.92, and 0.94, respectively. Therefore, the use of pretrained CNNs as feature extractors has the capability to enhance the efficiency and accuracy of chili disease identification in agricultural settings. |
| format | Article |
| id | my.uthm.eprints-12279 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | en |
| publishDate | 2024 |
| record_format | eprints |
| spelling | my.uthm.eprints-122792025-05-02T07:22:07Z http://eprints.uthm.edu.my/12279/ TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS FEATURE EXTRACTORS FOR CHILI LEAF IMAGES Aminuddin, Nuramin Fitri Abdul Kadir, Herdawatie Md Tomari, Mohd Razali Joret, Ariffuddin Tukiran, Zarina QA Mathematics Chili is a popular crop that is widely grown due to its flavorful and spicy fruit that is nutritionally beneficial. For the benefit of economic growth, it is important to precisely assess the chili health. With the advancement of computer vision-based applications, methods such as feature descriptors have been utilized to assist farm owners in identifying chili diseases via chili leaf images. However, these feature descriptors still require the manual extraction of disease features in order to accurately identify chili diseases. In this research, pretrained Convolutional Neural Networks (CNNs) are proposed as feature extractors to identify healthy and diseased chili leaf images. Three pretrained CNN models, DenseNet-201, EfficientNet-b0, and NasNet-Mobile, are utilized for their ability to identify healthy and diseased chili leaf using five indexes: accuracy, recall, specificity, precision, and F1-score. These indexes are validated through a five-fold cross-validation method during the experiments. The experimental results show that the EfficientNet-b0 model achieved the highest identification performance, with indexes of accuracy, recall, specificity, precision, and F1- score of 97.05%, 0.97, 0.92, 0.92, and 0.94, respectively. Therefore, the use of pretrained CNNs as feature extractors has the capability to enhance the efficiency and accuracy of chili disease identification in agricultural settings. 2024 Article PeerReviewed text en http://eprints.uthm.edu.my/12279/1/J17714_a2078c02b50c385a1088ef4c2b5ec6c0.pdf Aminuddin, Nuramin Fitri and Abdul Kadir, Herdawatie and Md Tomari, Mohd Razali and Joret, Ariffuddin and Tukiran, Zarina (2024) TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS FEATURE EXTRACTORS FOR CHILI LEAF IMAGES. Jurnal Teknologi, 86 (2). pp. 89-100. ISSN 2180–3722 https://doi.org/10.11113/jurnalteknologi.v86.19853%7C |
| spellingShingle | QA Mathematics Aminuddin, Nuramin Fitri Abdul Kadir, Herdawatie Md Tomari, Mohd Razali Joret, Ariffuddin Tukiran, Zarina TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS FEATURE EXTRACTORS FOR CHILI LEAF IMAGES |
| title | TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS
FEATURE EXTRACTORS FOR CHILI LEAF IMAGES |
| title_full | TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS
FEATURE EXTRACTORS FOR CHILI LEAF IMAGES |
| title_fullStr | TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS
FEATURE EXTRACTORS FOR CHILI LEAF IMAGES |
| title_full_unstemmed | TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS
FEATURE EXTRACTORS FOR CHILI LEAF IMAGES |
| title_short | TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS
FEATURE EXTRACTORS FOR CHILI LEAF IMAGES |
| title_sort | towards improved disease identification with pretrained convolutional neural networks as
feature extractors for chili leaf images |
| topic | QA Mathematics |
| url | http://eprints.uthm.edu.my/12279/1/J17714_a2078c02b50c385a1088ef4c2b5ec6c0.pdf http://eprints.uthm.edu.my/12279/ https://doi.org/10.11113/jurnalteknologi.v86.19853%7C |
| url_provider | http://eprints.uthm.edu.my/ |