Plant Disease Classifier: Detection of Dual-Crop Diseases Using Lightweight 2D CNN Architecture
Tomatoes are the most widely grown crop in the world, and they may be found in a variety of forms in every kitchen, regardless of cuisine. It is, after potato and sweet potato, the most widely farmed crop on the planet. Cotton is another essential cash crop because most farmers grow it in huge quant...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10267978/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554017998602240 |
|---|---|
| author | Hasibul Islam Peyal Md. Nahiduzzaman Md. Abu Hanif Pramanik Md. Khalid Syfullah Saleh Mohammed Shahriar Abida Sultana Mominul Ahsan Julfikar Haider Amith Khandakar Muhammad E. H. Chowdhury |
| author_facet | Hasibul Islam Peyal Md. Nahiduzzaman Md. Abu Hanif Pramanik Md. Khalid Syfullah Saleh Mohammed Shahriar Abida Sultana Mominul Ahsan Julfikar Haider Amith Khandakar Muhammad E. H. Chowdhury |
| author_sort | Hasibul Islam Peyal |
| collection | DOAJ |
| description | Tomatoes are the most widely grown crop in the world, and they may be found in a variety of forms in every kitchen, regardless of cuisine. It is, after potato and sweet potato, the most widely farmed crop on the planet. Cotton is another essential cash crop because most farmers grow it in huge quantities. However, many diseases reduce the quality and quantity of tomato and cotton crops, resulting in a significant loss in production and productivity. It is critical to detect these disorders at an early stage of diagnosis. The purpose of this work is to categorize 14 classes for both cotton and tomato crops, with 12 diseased classes and two healthy classes using a deep learning-based lightweight 2D CNN architecture and to implement the model in an android application named “Plant Disease Classifier” for smartphone-assisted plant disease diagnosis system, the results of the experiments reveal that the proposed model outperforms the pre-trained models VGG16, VGG19 and InceptionV3 despite having fewer parameters. With slightly larger parameters than MobileNet and MobileNetV2, proposed model also attains considerably larger accuracy than these models. The classification accuracy varies between 57% and 92% for these models, and the proposed model’s average accuracy is 97.36%. Also, the precision, recall, F1-score of the proposed model is 97 % and Area Under Curve (AUC) score of the model is 99.9% which is an indicator of the very good performance of the model. Class activation maps were shown using the Gradient Weighted Class Activation Mapping (Grad-CAM) technique to visually explain the disease detected by the proposed model, and a heatmap was produced to indicate the responsible region for classification. The app works very impressively and classified the correct disease in a shorter period of time of about 4.84 ms due to the lightweight nature of the model. |
| format | Article |
| id | doaj-art-22506aa7413146fc83335e05feefaab6 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-22506aa7413146fc83335e05feefaab62025-01-09T00:00:38ZengIEEEIEEE Access2169-35362023-01-011111062711064310.1109/ACCESS.2023.332068610267978Plant Disease Classifier: Detection of Dual-Crop Diseases Using Lightweight 2D CNN ArchitectureHasibul Islam Peyal0Md. Nahiduzzaman1https://orcid.org/0000-0003-4126-0389Md. Abu Hanif Pramanik2Md. Khalid Syfullah3https://orcid.org/0000-0001-7771-4587Saleh Mohammed Shahriar4Abida Sultana5Mominul Ahsan6https://orcid.org/0000-0002-7300-506XJulfikar Haider7https://orcid.org/0000-0001-7010-8285Amith Khandakar8https://orcid.org/0000-0001-7068-9112Muhammad E. H. Chowdhury9https://orcid.org/0000-0003-0744-8206Department of Computer Science and Engineering, Rajshahi University of Engineering and Technology, Rajshahi, BangladeshDepartment of Electrical and Computer Engineering, Rajshahi University of Engineering and Technology, Rajshahi, BangladeshDepartment of Electrical and Computer Engineering, Rajshahi University of Engineering and Technology, Rajshahi, BangladeshDepartment of Electrical and Computer Engineering, Rajshahi University of Engineering and Technology, Rajshahi, BangladeshDepartment of Electrical and Computer Engineering, Rajshahi University of Engineering and Technology, Rajshahi, BangladeshDepartment of Computer Science and Engineering, Uttara University, Dhaka, BangladeshDepartment of Computer Science, University of York, York, U.KDepartment of Engineering, Manchester Metropolitan University, Manchester, U.KDepartment of Electrical Engineering, Qatar University, Doha, QatarDepartment of Electrical Engineering, Qatar University, Doha, QatarTomatoes are the most widely grown crop in the world, and they may be found in a variety of forms in every kitchen, regardless of cuisine. It is, after potato and sweet potato, the most widely farmed crop on the planet. Cotton is another essential cash crop because most farmers grow it in huge quantities. However, many diseases reduce the quality and quantity of tomato and cotton crops, resulting in a significant loss in production and productivity. It is critical to detect these disorders at an early stage of diagnosis. The purpose of this work is to categorize 14 classes for both cotton and tomato crops, with 12 diseased classes and two healthy classes using a deep learning-based lightweight 2D CNN architecture and to implement the model in an android application named “Plant Disease Classifier” for smartphone-assisted plant disease diagnosis system, the results of the experiments reveal that the proposed model outperforms the pre-trained models VGG16, VGG19 and InceptionV3 despite having fewer parameters. With slightly larger parameters than MobileNet and MobileNetV2, proposed model also attains considerably larger accuracy than these models. The classification accuracy varies between 57% and 92% for these models, and the proposed model’s average accuracy is 97.36%. Also, the precision, recall, F1-score of the proposed model is 97 % and Area Under Curve (AUC) score of the model is 99.9% which is an indicator of the very good performance of the model. Class activation maps were shown using the Gradient Weighted Class Activation Mapping (Grad-CAM) technique to visually explain the disease detected by the proposed model, and a heatmap was produced to indicate the responsible region for classification. The app works very impressively and classified the correct disease in a shorter period of time of about 4.84 ms due to the lightweight nature of the model.https://ieeexplore.ieee.org/document/10267978/Convolution neural network (CNN)lightweight 2D CNNandroid applicationplant disease diagnosis systemgradient weighted class activation mapping (Grad-CAM)tomato |
| spellingShingle | Hasibul Islam Peyal Md. Nahiduzzaman Md. Abu Hanif Pramanik Md. Khalid Syfullah Saleh Mohammed Shahriar Abida Sultana Mominul Ahsan Julfikar Haider Amith Khandakar Muhammad E. H. Chowdhury Plant Disease Classifier: Detection of Dual-Crop Diseases Using Lightweight 2D CNN Architecture IEEE Access Convolution neural network (CNN) lightweight 2D CNN android application plant disease diagnosis system gradient weighted class activation mapping (Grad-CAM) tomato |
| title | Plant Disease Classifier: Detection of Dual-Crop Diseases Using Lightweight 2D CNN Architecture |
| title_full | Plant Disease Classifier: Detection of Dual-Crop Diseases Using Lightweight 2D CNN Architecture |
| title_fullStr | Plant Disease Classifier: Detection of Dual-Crop Diseases Using Lightweight 2D CNN Architecture |
| title_full_unstemmed | Plant Disease Classifier: Detection of Dual-Crop Diseases Using Lightweight 2D CNN Architecture |
| title_short | Plant Disease Classifier: Detection of Dual-Crop Diseases Using Lightweight 2D CNN Architecture |
| title_sort | plant disease classifier detection of dual crop diseases using lightweight 2d cnn architecture |
| topic | Convolution neural network (CNN) lightweight 2D CNN android application plant disease diagnosis system gradient weighted class activation mapping (Grad-CAM) tomato |
| url | https://ieeexplore.ieee.org/document/10267978/ |
| work_keys_str_mv | AT hasibulislampeyal plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT mdnahiduzzaman plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT mdabuhanifpramanik plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT mdkhalidsyfullah plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT salehmohammedshahriar plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT abidasultana plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT mominulahsan plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT julfikarhaider plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT amithkhandakar plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture AT muhammadehchowdhury plantdiseaseclassifierdetectionofdualcropdiseasesusinglightweight2dcnnarchitecture |