Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases Classification
Early detection of plant diseases is essential for effective crop disease management to prevent yield loss. In this study, we developed a methodology for classifying diseases in rice leaves using four deep learning models and a dataset with 2658 images of healthy and diseased rice leaves. Four model...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10458944/ |
| _version_ | 1827308264947187712 |
|---|---|
| author | Wassem I. A. E. Altabaji Muhammad Umair Wooi-Haw Tan Yee-Loo Foo Chee-Pun Ooi |
| author_facet | Wassem I. A. E. Altabaji Muhammad Umair Wooi-Haw Tan Yee-Loo Foo Chee-Pun Ooi |
| author_sort | Wassem I. A. E. Altabaji |
| collection | DOAJ |
| description | Early detection of plant diseases is essential for effective crop disease management to prevent yield loss. In this study, we developed a methodology for classifying diseases in rice leaves using four deep learning models and a dataset with 2658 images of healthy and diseased rice leaves. Four models, namely LeafNet, Modified LeafNet, MobileNetV2, and Xception, were compared. The Modified LeafNet model involved updates to LeafNet’s architectural parameters, whereas transfer learning techniques were applied to the MobileNetV2 and Xception pretrained models. The optimal hyperparameters for training were determined by considering several factors such as batch size, data augmentation, learning rate, and optimizers. The Modified LeafNet model achieved the highest accuracies of 97.44% and 87.76% for the validation and testing datasets, respectively. In comparison, LeafNet obtained 88.92% and 71.84%, Xception obtained 88.64% and 71.95%, and MobileNetV2 obtained 82.10% and 67.68% for the validation and test accuracies on the same datasets, respectively. This study contributes to the development of automated disease classification systems for rice leaves, thereby leading to increased agricultural productivity and sustainability. |
| first_indexed | 2024-04-24T18:54:19Z |
| format | Article |
| id | doaj.art-bbeb3c935caf42a88644695073728d3d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T18:54:19Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-bbeb3c935caf42a88644695073728d3d2024-03-26T17:45:57ZengIEEEIEEE Access2169-35362024-01-0112366223663510.1109/ACCESS.2024.337300010458944Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases ClassificationWassem I. A. E. Altabaji0https://orcid.org/0009-0008-5161-7920Muhammad Umair1https://orcid.org/0000-0003-3971-2067Wooi-Haw Tan2https://orcid.org/0000-0002-0436-0391Yee-Loo Foo3https://orcid.org/0000-0001-6106-4655Chee-Pun Ooi4https://orcid.org/0000-0003-2868-8866Faculty of Engineering, Multimedia University, Cyberjaya, Selangor, MalaysiaFaculty of Engineering, Multimedia University, Cyberjaya, Selangor, MalaysiaFaculty of Engineering, Multimedia University, Cyberjaya, Selangor, MalaysiaFaculty of Engineering, Multimedia University, Cyberjaya, Selangor, MalaysiaFaculty of Engineering, Multimedia University, Cyberjaya, Selangor, MalaysiaEarly detection of plant diseases is essential for effective crop disease management to prevent yield loss. In this study, we developed a methodology for classifying diseases in rice leaves using four deep learning models and a dataset with 2658 images of healthy and diseased rice leaves. Four models, namely LeafNet, Modified LeafNet, MobileNetV2, and Xception, were compared. The Modified LeafNet model involved updates to LeafNet’s architectural parameters, whereas transfer learning techniques were applied to the MobileNetV2 and Xception pretrained models. The optimal hyperparameters for training were determined by considering several factors such as batch size, data augmentation, learning rate, and optimizers. The Modified LeafNet model achieved the highest accuracies of 97.44% and 87.76% for the validation and testing datasets, respectively. In comparison, LeafNet obtained 88.92% and 71.84%, Xception obtained 88.64% and 71.95%, and MobileNetV2 obtained 82.10% and 67.68% for the validation and test accuracies on the same datasets, respectively. This study contributes to the development of automated disease classification systems for rice leaves, thereby leading to increased agricultural productivity and sustainability.https://ieeexplore.ieee.org/document/10458944/Deep learningconvolutional neural networkstransfer learningimage classification |
| spellingShingle | Wassem I. A. E. Altabaji Muhammad Umair Wooi-Haw Tan Yee-Loo Foo Chee-Pun Ooi Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases Classification IEEE Access Deep learning convolutional neural networks transfer learning image classification |
| title | Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases Classification |
| title_full | Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases Classification |
| title_fullStr | Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases Classification |
| title_full_unstemmed | Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases Classification |
| title_short | Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases Classification |
| title_sort | comparative analysis of transfer learning leafnet and modified leafnet models for accurate rice leaf diseases classification |
| topic | Deep learning convolutional neural networks transfer learning image classification |
| url | https://ieeexplore.ieee.org/document/10458944/ |
| work_keys_str_mv | AT wassemiaealtabaji comparativeanalysisoftransferlearningleafnetandmodifiedleafnetmodelsforaccuratericeleafdiseasesclassification AT muhammadumair comparativeanalysisoftransferlearningleafnetandmodifiedleafnetmodelsforaccuratericeleafdiseasesclassification AT wooihawtan comparativeanalysisoftransferlearningleafnetandmodifiedleafnetmodelsforaccuratericeleafdiseasesclassification AT yeeloofoo comparativeanalysisoftransferlearningleafnetandmodifiedleafnetmodelsforaccuratericeleafdiseasesclassification AT cheepunooi comparativeanalysisoftransferlearningleafnetandmodifiedleafnetmodelsforaccuratericeleafdiseasesclassification |