Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement
Improving agricultural productivity is essential due to rapid population growth, making early detection of crop diseases crucial. Although deep learning shows promise in smart agriculture, practical applications for identifying wheat diseases in complex backgrounds are limited. In this paper, we pro...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-07-01
|
| Series: | AgriEngineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-7402/6/3/117 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850258762326081536 |
|---|---|
| author | Oumayma Jouini Mohamed Ould-Elhassen Aoueileyine Kaouthar Sethom Anis Yazidi |
| author_facet | Oumayma Jouini Mohamed Ould-Elhassen Aoueileyine Kaouthar Sethom Anis Yazidi |
| author_sort | Oumayma Jouini |
| collection | DOAJ |
| description | Improving agricultural productivity is essential due to rapid population growth, making early detection of crop diseases crucial. Although deep learning shows promise in smart agriculture, practical applications for identifying wheat diseases in complex backgrounds are limited. In this paper, we propose CropNet, a hybrid method that utilizes Red, Green, and Blue (RGB) imaging and a transfer learning approach combined with shallow convolutional neural networks (CNN) for further feature refinement. To develop our customized model, we conducted an extensive search for the optimal deep learning architecture. Our approach involves freezing the pre-trained model for feature extraction and adding a custom trainable CNN layer. Unlike traditional transfer learning, which typically uses trainable dense layers, our method integrates a trainable CNN, deepening the architecture. We argue that pre-trained features in transfer learning are better suited for a custom shallow CNN followed by a fully connected layer, rather than being fed directly into fully connected layers. We tested various architectures for pre-trained models including EfficientNetB0 and B2, DenseNet, ResNet50, MobileNetV2, MobileNetV3-Small, and Inceptionv3. Our approach combines the strengths of pre-trained models with the flexibility of custom architecture design, offering efficiency, effective feature extraction, customization options, reduced overfitting, and differential learning rates. It distinguishes itself from classical transfer learning techniques, which typically fine-tune the entire pre-trained network. Our aim is to provide a lightweight model suitable for resource-constrained environments, capable of delivering outstanding results. CropNet achieved 99.80% accuracy in wheat disease detection with reduced training time and computational cost. This efficient performance makes CropNet promising for practical implementation in resource-constrained agricultural settings, benefiting farmers and enhancing production. |
| format | Article |
| id | doaj-art-63d94ff431064589ba9850d79b9cbc86 |
| institution | OA Journals |
| issn | 2624-7402 |
| language | English |
| publishDate | 2024-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AgriEngineering |
| spelling | doaj-art-63d94ff431064589ba9850d79b9cbc862025-08-20T01:56:02ZengMDPI AGAgriEngineering2624-74022024-07-01632001202210.3390/agriengineering6030117Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature RefinementOumayma Jouini0Mohamed Ould-Elhassen Aoueileyine1Kaouthar Sethom2Anis Yazidi3Innov’COM Laboratory, Higher School of Communication of Tunis (SUPCOM), Technopark Elghazala, Raoued, Ariana 2083, TunisiaInnov’COM Laboratory, Higher School of Communication of Tunis (SUPCOM), Technopark Elghazala, Raoued, Ariana 2083, TunisiaInnov’COM Laboratory, Higher School of Communication of Tunis (SUPCOM), Technopark Elghazala, Raoued, Ariana 2083, TunisiaDepartment of Computer Science, OsloMet–Oslo Metropolitan University, 0176 Oslo, NorwayImproving agricultural productivity is essential due to rapid population growth, making early detection of crop diseases crucial. Although deep learning shows promise in smart agriculture, practical applications for identifying wheat diseases in complex backgrounds are limited. In this paper, we propose CropNet, a hybrid method that utilizes Red, Green, and Blue (RGB) imaging and a transfer learning approach combined with shallow convolutional neural networks (CNN) for further feature refinement. To develop our customized model, we conducted an extensive search for the optimal deep learning architecture. Our approach involves freezing the pre-trained model for feature extraction and adding a custom trainable CNN layer. Unlike traditional transfer learning, which typically uses trainable dense layers, our method integrates a trainable CNN, deepening the architecture. We argue that pre-trained features in transfer learning are better suited for a custom shallow CNN followed by a fully connected layer, rather than being fed directly into fully connected layers. We tested various architectures for pre-trained models including EfficientNetB0 and B2, DenseNet, ResNet50, MobileNetV2, MobileNetV3-Small, and Inceptionv3. Our approach combines the strengths of pre-trained models with the flexibility of custom architecture design, offering efficiency, effective feature extraction, customization options, reduced overfitting, and differential learning rates. It distinguishes itself from classical transfer learning techniques, which typically fine-tune the entire pre-trained network. Our aim is to provide a lightweight model suitable for resource-constrained environments, capable of delivering outstanding results. CropNet achieved 99.80% accuracy in wheat disease detection with reduced training time and computational cost. This efficient performance makes CropNet promising for practical implementation in resource-constrained agricultural settings, benefiting farmers and enhancing production.https://www.mdpi.com/2624-7402/6/3/117wheat leaf diseasesdeep learningtransfer learninghybrid modellightweight modeledge device |
| spellingShingle | Oumayma Jouini Mohamed Ould-Elhassen Aoueileyine Kaouthar Sethom Anis Yazidi Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement AgriEngineering wheat leaf diseases deep learning transfer learning hybrid model lightweight model edge device |
| title | Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement |
| title_full | Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement |
| title_fullStr | Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement |
| title_full_unstemmed | Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement |
| title_short | Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement |
| title_sort | wheat leaf disease detection a lightweight approach with shallow cnn based feature refinement |
| topic | wheat leaf diseases deep learning transfer learning hybrid model lightweight model edge device |
| url | https://www.mdpi.com/2624-7402/6/3/117 |
| work_keys_str_mv | AT oumaymajouini wheatleafdiseasedetectionalightweightapproachwithshallowcnnbasedfeaturerefinement AT mohamedouldelhassenaoueileyine wheatleafdiseasedetectionalightweightapproachwithshallowcnnbasedfeaturerefinement AT kaoutharsethom wheatleafdiseasedetectionalightweightapproachwithshallowcnnbasedfeaturerefinement AT anisyazidi wheatleafdiseasedetectionalightweightapproachwithshallowcnnbasedfeaturerefinement |