A Channel Attention-Driven Optimized CNN for Efficient Early Detection of Plant Diseases in Resource Constrained Environment
Agriculture is a cornerstone of economic prosperity, but plant diseases can severely impact crop yield and quality. Identifying these diseases accurately is often difficult due to limited expert availability and ambiguous information. Early detection and automated diagnosis systems are crucial to mi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/2/127 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589465362628608 |
|---|---|
| author | Sana Parez Naqqash Dilshad Jong Weon Lee |
| author_facet | Sana Parez Naqqash Dilshad Jong Weon Lee |
| author_sort | Sana Parez |
| collection | DOAJ |
| description | Agriculture is a cornerstone of economic prosperity, but plant diseases can severely impact crop yield and quality. Identifying these diseases accurately is often difficult due to limited expert availability and ambiguous information. Early detection and automated diagnosis systems are crucial to mitigate these challenges. To address this, we propose a lightweight convolutional neural network (CNN) designed for resource-constrained devices termed as <i>LeafNet</i>. <i>LeafNet</i> draws inspiration from the block-wise VGG19 architecture but incorporates several optimizations, including a reduced number of parameters, smaller input size, and faster inference time while maintaining competitive accuracy. The proposed <i>LeafNet</i> leverages small, uniform convolutional filters to capture fine-grained details of plant disease features, with an increasing number of channels to enhance feature extraction. Additionally, it integrates channel attention mechanisms to prioritize disease-related features effectively. We evaluated the proposed method on four datasets: the benchmark plant village (PV), the data repository of leaf images (DRLIs), the newly curated plant composite (PC) dataset, and the BARI Sunflower (BARI-Sun) dataset, which includes diverse and challenging real-world images. The results show that the proposed performs comparably to state-of-the-art methods in terms of accuracy, false positive rate (FPR), model size, and runtime, highlighting its potential for real-world applications. |
| format | Article |
| id | doaj-art-46a079c5123e4fdaaf6e8454541e165a |
| institution | Kabale University |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-46a079c5123e4fdaaf6e8454541e165a2025-01-24T13:15:48ZengMDPI AGAgriculture2077-04722025-01-0115212710.3390/agriculture15020127A Channel Attention-Driven Optimized CNN for Efficient Early Detection of Plant Diseases in Resource Constrained EnvironmentSana Parez0Naqqash Dilshad1Jong Weon Lee2Department of Software, Sejong University, Seoul 05006, Republic of KoreaDepartment of Computer Science and Engineering, Sejong University, Seoul 05006, Republic of KoreaDepartment of Software, Sejong University, Seoul 05006, Republic of KoreaAgriculture is a cornerstone of economic prosperity, but plant diseases can severely impact crop yield and quality. Identifying these diseases accurately is often difficult due to limited expert availability and ambiguous information. Early detection and automated diagnosis systems are crucial to mitigate these challenges. To address this, we propose a lightweight convolutional neural network (CNN) designed for resource-constrained devices termed as <i>LeafNet</i>. <i>LeafNet</i> draws inspiration from the block-wise VGG19 architecture but incorporates several optimizations, including a reduced number of parameters, smaller input size, and faster inference time while maintaining competitive accuracy. The proposed <i>LeafNet</i> leverages small, uniform convolutional filters to capture fine-grained details of plant disease features, with an increasing number of channels to enhance feature extraction. Additionally, it integrates channel attention mechanisms to prioritize disease-related features effectively. We evaluated the proposed method on four datasets: the benchmark plant village (PV), the data repository of leaf images (DRLIs), the newly curated plant composite (PC) dataset, and the BARI Sunflower (BARI-Sun) dataset, which includes diverse and challenging real-world images. The results show that the proposed performs comparably to state-of-the-art methods in terms of accuracy, false positive rate (FPR), model size, and runtime, highlighting its potential for real-world applications.https://www.mdpi.com/2077-0472/15/2/127plant disease classificationsmart agricultureprecision farmingattention mechanismVGG19 |
| spellingShingle | Sana Parez Naqqash Dilshad Jong Weon Lee A Channel Attention-Driven Optimized CNN for Efficient Early Detection of Plant Diseases in Resource Constrained Environment Agriculture plant disease classification smart agriculture precision farming attention mechanism VGG19 |
| title | A Channel Attention-Driven Optimized CNN for Efficient Early Detection of Plant Diseases in Resource Constrained Environment |
| title_full | A Channel Attention-Driven Optimized CNN for Efficient Early Detection of Plant Diseases in Resource Constrained Environment |
| title_fullStr | A Channel Attention-Driven Optimized CNN for Efficient Early Detection of Plant Diseases in Resource Constrained Environment |
| title_full_unstemmed | A Channel Attention-Driven Optimized CNN for Efficient Early Detection of Plant Diseases in Resource Constrained Environment |
| title_short | A Channel Attention-Driven Optimized CNN for Efficient Early Detection of Plant Diseases in Resource Constrained Environment |
| title_sort | channel attention driven optimized cnn for efficient early detection of plant diseases in resource constrained environment |
| topic | plant disease classification smart agriculture precision farming attention mechanism VGG19 |
| url | https://www.mdpi.com/2077-0472/15/2/127 |
| work_keys_str_mv | AT sanaparez achannelattentiondrivenoptimizedcnnforefficientearlydetectionofplantdiseasesinresourceconstrainedenvironment AT naqqashdilshad achannelattentiondrivenoptimizedcnnforefficientearlydetectionofplantdiseasesinresourceconstrainedenvironment AT jongweonlee achannelattentiondrivenoptimizedcnnforefficientearlydetectionofplantdiseasesinresourceconstrainedenvironment AT sanaparez channelattentiondrivenoptimizedcnnforefficientearlydetectionofplantdiseasesinresourceconstrainedenvironment AT naqqashdilshad channelattentiondrivenoptimizedcnnforefficientearlydetectionofplantdiseasesinresourceconstrainedenvironment AT jongweonlee channelattentiondrivenoptimizedcnnforefficientearlydetectionofplantdiseasesinresourceconstrainedenvironment |